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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    APT
    -0.07
    _ARGS
    -0.07
     invented
    -0.06
     sce
    -0.06
     gens
    -0.06
     gad
    -0.06
    _selection
    -0.06
     hai
    -0.06
    DATED
    -0.06
    Ob
    -0.06
    POSITIVE LOGITS
     poverty
    0.06
    _]
    0.06
     तरफ
    0.06
     '_',
    0.06
    ыми
    0.06
    rava
    0.06
    >("
    0.06
     التش
    0.06
     معماری
    0.06
    .／
    0.06
    Act Density 0.067%

    No Known Activations