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

    Neuronpedia

    INDEX
    Explanations

    promise

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     우
    -0.07
    .Matchers
    -0.07
    ‐'
    -0.06
     onPause
    -0.06
     tercih
    -0.06
    .Driver
    -0.06
     pity
    -0.06
     trapped
    -0.06
    Parse
    -0.06
     Perception
    -0.06
    POSITIVE LOGITS
    BREAK
    0.07
    ária
    0.07
    faf
    0.07
    (EXPR
    0.06
    alia
    0.06
    _AV
    0.06
     �
    0.06
    bal
    0.06
     freeing
    0.06
    italize
    0.06
    Act Density 0.043%

    No Known Activations