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

    Neuronpedia

    INDEX
    Explanations

    budgeting and planning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fichier
    0.52
    ainan
    0.49
    ahiran
    0.45
    েয়
    0.44
    relation
    0.43
     efeitos
    0.42
     insegn
    0.42
    層
    0.42
     flammable
    0.41
    acetone
    0.41
    POSITIVE LOGITS
     Branding
    0.44
     renom
    0.42
    !,
    0.42
     zarówno
    0.41
     Gaming
    0.39
     Preview
    0.39
     Be
    0.39
    !:
    0.39
    Პ
    0.39
    !).
    0.38
    Act Density 0.002%

    No Known Activations