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

    Neuronpedia

    INDEX
    Explanations

    cancel

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     motiv
    -0.08
    形
    -0.08
     exponent
    -0.08
     ensemble
    -0.08
     machines
    -0.08
     erwerben
    -0.07
     jour
    -0.07
    頃
    -0.07
    挑
    -0.07
    부터
    -0.07
    POSITIVE LOGITS
     предотвращ
    0.13
    prevent
    0.12
    .prevent
    0.11
    Prevent
    0.11
     запрещ
    0.11
     prevent
    0.11
     Prevent
    0.11
     предот
    0.10
     veto
    0.10
    deny
    0.10
    Act Density 0.003%

    No Known Activations