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

    Neuronpedia

    INDEX
    Explanations

    active vs passive states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     организаций
    0.47
    Ꮡ
    0.44
    дина
    0.44
     кризи
    0.43
    Kum
    0.43
    mohan
    0.43
    tiers
    0.43
    가가
    0.42
    chard
    0.42
    dimensioni
    0.42
    POSITIVE LOGITS
     passive
    0.63
     Passive
    0.53
     passively
    0.49
    passive
    0.48
     viel
    0.46
    Passive
    0.45
     stub
    0.44
     obedience
    0.41
     نح
    0.40
     method
    0.40
    Act Density 0.013%

    No Known Activations