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

    Neuronpedia

    INDEX
    Explanations

    android manifest labels and ids

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     biting
    0.46
     billets
    0.44
    bracketing
    0.43
     vapors
    0.42
    boyfriend
    0.41
     knelt
    0.40
     torsion
    0.40
    dough
    0.40
     tarses
    0.40
     computeEncoder
    0.40
    POSITIVE LOGITS
    label
    0.77
     Label
    0.76
    exported
    0.75
     label
    0.73
    Label
    0.70
     Launch
    0.70
    Theme
    0.62
     exported
    0.60
    Launch
    0.59
    LABEL
    0.59
    Act Density 0.003%

    No Known Activations