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

    Neuronpedia

    INDEX
    Explanations

    ip

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kicker
    -0.08
     shelf
    -0.07
     　　 　
    -0.07
    表示
    -0.07
     encour
    -0.06
     reason
    -0.06
    '})↵↵
    -0.06
     Hãy
    -0.06
     \@
    -0.06
     sled
    -0.06
    POSITIVE LOGITS
    .Nombre
    0.07
    'elle
    0.07
    nard
    0.07
     BIND
    0.06
    riters
    0.06
    rary
    0.06
    teří
    0.06
    .pi
    0.06
     Hide
    0.06
    admins
    0.06
    Act Density 0.008%

    No Known Activations