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

    Neuronpedia

    INDEX
    Explanations

    veto

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ürlich
    -0.07
     disposable
    -0.06
     přid
    -0.06
    _DA
    -0.06
    .authService
    -0.06
    راد
    -0.06
    ちょ
    -0.06
     برخی
    -0.06
    .combine
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     Null
    0.07
    (lua
    0.07
     veto
    0.07
     Characters
    0.07
    /Header
    0.06
    checks
    0.06
     erle
    0.06
     Suffolk
    0.06
     Know
    0.06
    [cur
    0.06
    Act Density 0.002%

    No Known Activations