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

    Neuronpedia

    INDEX
    Explanations

    disability

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iology
    -0.07
    ana
    -0.07
    uggested
    -0.07
     symbol
    -0.06
    inue
    -0.06
     ports
    -0.06
     compound
    -0.06
     Clarkson
    -0.06
    Vault
    -0.06
     Vault
    -0.06
    POSITIVE LOGITS
     ｲ
    0.07
    gratis
    0.06
    Enemies
    0.06
     때문
    0.06
    .ease
    0.06
     figur
    0.06
    ="{{$
    0.06
     süresi
    0.06
     JO
    0.06
    _CONNECTION
    0.06
    Act Density 0.031%

    No Known Activations