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

    Neuronpedia

    INDEX
    Explanations

    names and associated titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sluggish
    0.54
     which
    0.52
     itself
    0.48
     consonant
    0.48
     drawbacks
    0.47
     specific
    0.47
     planar
    0.47
     absorbance
    0.47
     diminish
    0.46
     disjoint
    0.45
    POSITIVE LOGITS
     Jr
    1.28
    ová
    1.19
     jr
    1.17
    Jr
    1.04
     PhD
    1.03
     แห่ง
    1.02
     Sr
    1.01
     MBE
    0.97
    owski
    0.95
     Esq
    0.95
    Act Density 0.062%

    No Known Activations