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

    Neuronpedia

    INDEX
    Explanations

    arguments for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ermanfaat
    0.42
    <unused598>
    0.40
    .").
    0.39
    нням
    0.38
     현실
    0.38
     joueurs
    0.38
    !".
    0.38
    drama
    0.38
    皁
    0.38
    ガチャ
    0.38
    POSITIVE LOGITS
    Entire
    0.44
    Damage
    0.39
    Need
    0.37
    Count
    0.36
    POSITIVE
    0.36
     entire
    0.36
    Tech
    0.36
     pilots
    0.35
    Type
    0.35
    NOT
    0.34
    Act Density 0.016%

    No Known Activations