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

    Neuronpedia

    INDEX
    Explanations

    command-line instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .sourceforge
    -0.07
    .merge
    -0.06
    :::::::::
    -0.06
     Mirage
    -0.06
    όρ
    -0.06
    actual
    -0.06
    etype
    -0.06
    сяг
    -0.06
    joined
    -0.06
    ól
    -0.06
    POSITIVE LOGITS
     dangers
    0.08
     poisoned
    0.07
     Feast
    0.07
     reacting
    0.07
     televised
    0.06
    ما
    0.06
    페이지
    0.06
     Toggle
    0.06
     motor
    0.06
    [slot
    0.06
    Act Density 0.026%

    No Known Activations