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

    Neuronpedia

    INDEX
    Explanations

    R

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    EndTime
    -0.07
    nih
    -0.07
    efa
    -0.07
    license
    -0.07
     
    -0.06
     Şu
    -0.06
    ewn
    -0.06
    wap
    -0.06
    oya
    -0.06
    esture
    -0.06
    POSITIVE LOGITS
    odont
    0.08
     buyers
    0.06
    _AI
    0.06
    奪
    0.06
     contestants
    0.06
    Tokens
    0.06
     mr
    0.06
    _attribute
    0.06
     rebuilt
    0.06
    ารณ
    0.06
    Act Density 0.001%

    No Known Activations