Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Remembering and forgetting

    np_max-act · gemini-2.0-flash

    The neuron fires on conversational acknowledgement or concession phrases—instances where a speaker refers to their or the listener’s prior statements (e.g. “I know,” “you’ve told me,” “never tires of reminding us”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    921
    -0.07
     Saturday
    -0.07
    creation
    -0.07
    561
    -0.07
    verity
    -0.06
    Sanders
    -0.06
    937
    -0.06
     Increasing
    -0.06
     Royale
    -0.06
    .Obj
    -0.06
    POSITIVE LOGITS
    ayah
    0.07
    UIFont
    0.06
    _SENT
    0.06
    골
    0.06
     최고
    0.06
    /renderer
    0.06
    ську
    0.06
     tvoří
    0.06
     особ
    0.06
    _TOP
    0.06
    Act Density 0.107%

    No Known Activations