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

    Neuronpedia

    INDEX
    Explanations

    names and short phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     deleterious
    0.38
    ！」
    0.34
     promiscu
    0.33
    IRONMENT
    0.32
     "="
    0.32
    🕑
    0.32
     $=
    0.31
    Environment
    0.31
    бычно
    0.30
     extensively
    0.30
    POSITIVE LOGITS
     J
    0.38
    avat
    0.35
     Teatro
    0.34
     Ju
    0.33
     Vel
    0.33
    ifen
    0.32
     Sk
    0.32
     Cafe
    0.31
    bre
    0.31
     وش
    0.31
    Act Density 0.085%

    No Known Activations