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

    Neuronpedia

    INDEX
    Explanations

    illustration, factorization, ways

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    au
    0.43
    intosh
    0.43
     custodial
    0.41
    fragment
    0.40
    s
    0.40
    sm
    0.39
    ethylene
    0.39
     گذ
    0.38
    generating
    0.38
     pemilik
    0.38
    POSITIVE LOGITS
     dần
    0.51
     după
    0.47
    üsse
    0.47
    ivité
    0.47
     confirmé
    0.46
     TVs
    0.46
     maç
    0.45
    Spacing
    0.45
     após
    0.44
     După
    0.44
    Act Density 0.004%

    No Known Activations