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

    Neuronpedia

    INDEX
    Explanations

    trial

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cornerback
    -0.07
    Basically
    -0.06
     Commons
    -0.06
    uples
    -0.06
    ''"
    -0.06
    ajes
    -0.06
    _placement
    -0.06
     unseren
    -0.06
    aises
    -0.06
     math
    -0.06
    POSITIVE LOGITS
    ights
    0.08
     answered
    0.07
    uing
    0.07
     Guinness
    0.07
     Duel
    0.07
     exper
    0.06
     flies
    0.06
    Preparing
    0.06
    염
    0.06
    _response
    0.06
    Act Density 0.002%

    No Known Activations