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

    Neuronpedia

    INDEX
    Explanations

    The power of X / X of Y

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Feast
    0.47
    Epic
    0.40
    🥳
    0.39
     feast
    0.38
    诀
    0.38
    huge
    0.38
    AFP
    0.37
    Passport
    0.37
     Bites
    0.36
     unforgettable
    0.36
    POSITIVE LOGITS
     derivation
    0.51
     deleting
    0.47
     orthogon
    0.46
     derivations
    0.44
     orthogonality
    0.44
     geomet
    0.43
     aloud
    0.43
     ordinal
    0.43
     nilpotent
    0.43
     semicol
    0.43
    Act Density 0.000%

    No Known Activations