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

    Neuronpedia

    INDEX
    Explanations

    what's your or what's the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ใด
    0.97
    何を
    0.94
     뭘
    0.93
    Either
    0.84
    alnız
    0.84
    Anything
    0.83
    뭘
    0.83
    What
    0.82
    сій
    0.82
     ništa
    0.81
    POSITIVE LOGITS
     some
    1.22
     the
    1.10
    一些
    1.03
     your
    0.95
     happening
    0.92
     najleps
    0.91
     their
    0.91
     acceptable
    0.89
     alguns
    0.86
     entailed
    0.85
    Act Density 0.199%

    No Known Activations