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

    Neuronpedia

    INDEX
    Explanations

    punctuation and equals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     interpolation
    -0.09
    _interp
    -0.08
     invitados
    -0.08
    Interpolation
    -0.08
    cement
    -0.08
    nag
    -0.08
     interpolate
    -0.08
     flexibil
    -0.07
    _cli
    -0.07
    .Design
    -0.07
    POSITIVE LOGITS
    aderno
    0.08
    aju
    0.08
     Dyson
    0.08
    appa
    0.08
    andos
    0.08
    itamente
    0.08
     Quaternion
    0.07
     vitória
    0.07
    dy
    0.07
     Mink
    0.07
    Act Density 0.051%

    No Known Activations