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

    Neuronpedia

    INDEX
    Explanations

    agent

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    egas
    -0.07
     Pitch
    -0.06
    orex
    -0.06
    imax
    -0.06
     نامه
    -0.06
    оля
    -0.06
    ente
    -0.06
     FM
    -0.06
    jud
    -0.06
    ُر
    -0.06
    POSITIVE LOGITS
    hya
    0.07
    -founder
    0.06
    权
    0.06
    _ops
    0.06
    esModule
    0.06
     належ
    0.06
     nawet
    0.06
    )})↵
    0.06
    Adj
    0.06
    -save
    0.06
    Act Density 0.038%

    No Known Activations