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

    Neuronpedia

    INDEX
    Explanations

    Statistical results

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Yad
    -0.07
     touchdown
    -0.07
    束
    -0.07
     lesbian
    -0.07
    ADDR
    -0.07
     lesbians
    -0.07
    atore
    -0.06
    �
    -0.06
    _groups
    -0.06
    CONS
    -0.06
    POSITIVE LOGITS
    �
    0.07
    ritable
    0.06
    @Controller
    0.06
    .Batch
    0.06
    INGTON
    0.06
    modelName
    0.06
    azard
    0.06
    .;.;.;.;
    0.06
     �
    0.06
     �
    0.06
    Act Density 0.084%

    No Known Activations