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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -modal
    -0.07
    .weixin
    -0.06
    361
    -0.06
    plen
    -0.06
     بعد
    -0.06
    _dictionary
    -0.06
    _definition
    -0.06
    _default
    -0.06
     responseObject
    -0.06
     Unsigned
    -0.06
    POSITIVE LOGITS
     localization
    0.07
     Jing
    0.07
     Applications
    0.07
     aque
    0.06
     AMS
    0.06
    TERS
    0.06
    InvalidArgumentException
    0.06
    _Dec
    0.06
     Consumers
    0.06
    ığ
    0.06
    Act Density 0.078%

    No Known Activations