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

    Neuronpedia

    INDEX
    Explanations

    decision for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pastries
    0.41
     Standing
    0.40
     determination
    0.37
    范围
    0.36
    彧
    0.36
     millió
    0.36
     braid
    0.35
     Baz
    0.35
     Background
    0.35
     refill
    0.35
    POSITIVE LOGITS
    evi
    0.42
    meyer
    0.39
    ٣
    0.38
     terão
    0.38
     situazioni
    0.38
    bandit
    0.38
    orent
    0.37
    superuser
    0.37
    facility
    0.37
    tront
    0.37
    Act Density 0.000%

    No Known Activations