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

    Neuronpedia

    INDEX
    Explanations

    file paths and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tale
    -0.08
    hti
    -0.07
    ############################################################
    -0.07
    -Agent
    -0.07
     apresent
    -0.06
    STYLE
    -0.06
    untary
    -0.06
    assembly
    -0.06
    ITCH
    -0.06
    quence
    -0.06
    POSITIVE LOGITS
    жи
    0.06
    tuğ
    0.06
     ам
    0.06
    _slot
    0.06
    _rf
    0.06
     yaşında
    0.06
    razione
    0.06
    .into
    0.06
    _RENDERER
    0.06
     surprises
    0.05
    Act Density 0.017%

    No Known Activations