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

    Neuronpedia

    INDEX
    Explanations

    often

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     comedy
    -0.07
     baseman
    -0.07
    -call
    -0.07
     boys
    -0.06
     Chains
    -0.06
    Expand
    -0.06
    .assertThat
    -0.06
    TexImage
    -0.06
    áty
    -0.06
    _agent
    -0.06
    POSITIVE LOGITS
     dolor
    0.06
     đặt
    0.06
    iná
    0.06
     admins
    0.06
    WithValue
    0.06
     de
    0.06
     ｉ
    0.06
     uluslararası
    0.06
    şk
    0.06
    ��
    0.06
    Act Density 0.056%

    No Known Activations