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

    Neuronpedia

    INDEX
    Explanations

    kotlin code and programs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <0x80>
    0.66
    愔
    0.60
     synchronization
    0.58
     ablation
    0.56
    ст
    0.55
     Mongol
    0.55
    0.54
     festiv
    0.54
    0.53
    ｓ
    0.53
    POSITIVE LOGITS
    ano
    0.70
    ena
    0.70
    ac
    0.68
    asters
    0.64
    kotlin
    0.63
    ov
    0.63
    osas
    0.63
    eno
    0.61
     सफर
    0.61
    ásticos
    0.61
    Act Density 0.020%

    No Known Activations