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

    Neuronpedia

    INDEX
    Explanations

    allumer, alloggiamento, allarme, allineare

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gel
    0.44
     torn
    0.42
     uji
    0.42
     coprime
    0.41
     Tutto
    0.39
    saint
    0.39
    nats
    0.38
    winkel
    0.38
     тот
    0.38
     oma
    0.37
    POSITIVE LOGITS
    incer
    0.39
    ége
    0.39
    umption
    0.39
    uman
    0.38
    arga
    0.38
    onton
    0.37
    ונ
    0.37
    onta
    0.37
     Brooke
    0.37
    arme
    0.37
    Act Density 0.000%

    No Known Activations