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

    Neuronpedia

    INDEX
    Explanations

    approximations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _SEARCH
    -0.07
    elp
    -0.06
    .prom
    -0.06
    ЙЙ
    -0.06
     shook
    -0.06
     السعودية
    -0.06
     deter
    -0.06
    ичного
    -0.06
     Fakült
    -0.06
    ENV
    -0.06
    POSITIVE LOGITS
     �
    0.07
     های
    0.07
     Deal
    0.07
     милли
    0.07
     erle
    0.06
    返回
    0.06
    <'
    0.06
    Nonce
    0.06
     banc
    0.06
    /job
    0.06
    Act Density 0.024%

    No Known Activations