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

    Neuronpedia

    INDEX
    Explanations

    Hedgehogs and porcupines

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of porcupines and their quills—i.e. the word “porcupine” (subword “porcup”) and related quill-spike terms.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .Logf
    -0.07
    �
    -0.07
    すべて
    -0.06
    Level
    -0.06
    .algorithm
    -0.06
     halftime
    -0.06
    olang
    -0.06
     situated
    -0.06
     defeating
    -0.06
    -0.06
    POSITIVE LOGITS
     GFP
    0.07
    .InnerException
    0.07
     Pompe
    0.06
    -text
    0.06
    aguay
    0.06
     시험
    0.06
    inium
    0.06
     textured
    0.06
    illum
    0.06
    込み
    0.06
    Act Density 0.004%

    No Known Activations