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

    Neuronpedia

    INDEX
    Explanations

    important advice or steps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    amp
    0.50
    or
    0.50
    uma
    0.48
    ci
    0.48
    з
    0.47
    isp
    0.45
     هناك
    0.44
    amps
    0.43
    akukan
    0.43
    om
    0.42
    POSITIVE LOGITS
     servitude
    0.48
     respiration
    0.46
     oscillations
    0.45
     circulation
    0.44
     ambiguities
    0.43
     racing
    0.42
     overse
    0.42
     NOVEMBER
    0.40
     userInfo
    0.40
     oscillation
    0.39
    Act Density 0.000%

    No Known Activations