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

    Neuronpedia

    INDEX
    Explanations

    Negative/opinionated text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _sv
    -0.07
    Cur
    -0.06
    μμα
    -0.06
     Env
    -0.06
    ...,
    -0.06
    �
    -0.06
     OID
    -0.06
     �
    -0.06
     radicals
    -0.06
    _dn
    -0.06
    POSITIVE LOGITS
    =is
    0.07
    _DATABASE
    0.06
     البل
    0.06
    Inactive
    0.06
    .AddScoped
    0.06
     vẻ
    0.06
     skating
    0.06
    ixo
    0.06
     byl
    0.06
     İşte
    0.06
    Act Density 0.185%

    No Known Activations