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

    Neuronpedia

    INDEX
    Explanations

    grams

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     checkpoints
    -0.06
    ampions
    -0.06
     Escape
    -0.06
     keyof
    -0.06
     clinicians
    -0.06
     childbirth
    -0.06
    eventType
    -0.06
    ayıp
    -0.06
     Facebook
    -0.06
    /files
    -0.06
    POSITIVE LOGITS
    ~~~~
    0.06
    Ин
    0.06
    uencia
    0.06
     gerne
    0.06
    .SaveChanges
    0.06
    fre
    0.06
    नल
    0.06
    .SelectCommand
    0.06
    青
    0.06
    _BO
    0.06
    Act Density 0.014%

    No Known Activations