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

    Neuronpedia

    INDEX
    Explanations

    F

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     drought
    -0.07
    idar
    -0.07
    _targets
    -0.06
     juicy
    -0.06
     روم
    -0.06
     }}↵
    -0.06
    )].
    -0.06
    ativos
    -0.05
    _kv
    -0.05
     blanco
    -0.05
    POSITIVE LOGITS
     spindle
    0.13
     rod
    0.13
    ervatives
    0.10
    amines
    0.08
     steril
    0.08
    amı
    0.07
     Jame
    0.07
     pixel
    0.07
    Bill
    0.06
    _/
    0.06
    Act Density 0.004%

    No Known Activations