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

    Neuronpedia

    INDEX
    Explanations

    census data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    เหม
    -0.08
    .runner
    -0.07
     طل
    -0.07
    idon
    -0.06
    leich
    -0.06
     Slo
    -0.06
     Ian
    -0.06
    _ln
    -0.06
    rech
    -0.06
     igual
    -0.06
    POSITIVE LOGITS
     Autos
    0.07
     wrestlers
    0.06
    {}]
    0.06
    ×
    0.06
    UPDATE
    0.06
     vag
    0.06
    0.06
    -yyyy
    0.06
     Decrypt
    0.06
    estination
    0.06
    Act Density 0.001%

    No Known Activations