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

    Neuronpedia

    INDEX
    Explanations

    best

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _(
    -0.06
    _study
    -0.06
    现
    -0.06
     demokrat
    -0.06
     recuper
    -0.06
    .models
    -0.06
    .NotFound
    -0.06
     推
    -0.06
     valide
    -0.06
     PV
    -0.06
    POSITIVE LOGITS
    best
    0.07
     Most
    0.07
     disillusion
    0.06
    HONE
    0.06
     Planner
    0.06
     finer
    0.06
    .fill
    0.06
     lies
    0.06
    YTE
    0.06
    还有
    0.06
    Act Density 0.010%

    No Known Activations