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

    Neuronpedia

    INDEX
    Explanations

    dating and relationships

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect superlative or hyperbolic positive words and phrases (e.g. “best,” “ever,” “amazing,” “experience”) that express peak intensity or approval.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     semaphore
    -0.06
    .Rec
    -0.06
     �
    -0.06
     αφ
    -0.06
    �
    -0.06
    beeld
    -0.06
    acción
    -0.06
    /exp
    -0.06
     (_,
    -0.06
     Islanders
    -0.06
    POSITIVE LOGITS
     siguientes
    0.07
     причин
    0.07
     تاریخی
    0.06
    PF
    0.06
     comply
    0.06
    anks
    0.06
    _gpio
    0.06
    TreeNode
    0.06
     rámci
    0.06
     associates
    0.06
    Act Density 0.031%

    No Known Activations