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

    Neuronpedia

    INDEX
    Explanations

    conditions and situations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     furthering
    0.95
     underpin
    0.88
     articulating
    0.86
     encompass
    0.83
     foundational
    0.82
    こうした
    0.78
     individu
    0.77
     putative
    0.76
     reimag
    0.75
    計測
    0.75
    POSITIVE LOGITS
     丨
    1.16
     According
    1.09
     viciss
    1.08
     indiscrimin
    1.07
    According
    1.05
     signboard
    1.04
     incompar
    1.03
     unconsciously
    1.02
     scolded
    1.01
     ～
    1.01
    Act Density 0.017%

    No Known Activations