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

    Neuronpedia

    INDEX
    Explanations

    game, courses, career

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Fujifilm
    0.51
     Keystone
    0.51
     AsyncStorage
    0.50
     Conservative
    0.49
     Heat
    0.48
     frosty
    0.47
     dramatic
    0.47
     Morgen
    0.47
     Psychology
    0.47
     heatmap
    0.46
    POSITIVE LOGITS
    ans
    0.54
    usam
    0.54
    ai
    0.52
    im
    0.50
    atk
    0.50
    itles
    0.49
     aprov
    0.49
    olong
    0.49
    ud
    0.48
    aties
    0.48
    Act Density 0.000%

    No Known Activations