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

    Neuronpedia

    INDEX
    Explanations

    say the ending ')' or '*'

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .stringValue
    -0.08
    _ok
    -0.07
    VarInsn
    -0.07
    .Cons
    -0.07
    ucs
    -0.07
    nota
    -0.07
     lots
    -0.06
     cham
    -0.06
    �
    -0.06
     Turing
    -0.06
    POSITIVE LOGITS
    ('-',
    0.07
    阐释
    0.07
     hiếm
    0.07
     oppress
    0.07
    ນ
    0.06
    ерь
    0.06
    鹽
    0.06
     większe
    0.06
    侦察
    0.06
    พลาด
    0.06
    Act Density 0.001%

    No Known Activations