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

    Neuronpedia

    INDEX
    Explanations

    generating outlines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Transitions
    0.40
    nicu
    0.38
    ಂಟ
    0.37
     contests
    0.36
    諷
    0.36
     transitions
    0.36
    wrs
    0.36
     satd
    0.35
    SUB
    0.35
    stricken
    0.35
    POSITIVE LOGITS
    Instant
    0.38
     দেবতার
    0.38
     ус
    0.38
     அதிசய
    0.38
     (^{
    0.38
     waterfall
    0.38
    gles
    0.38
     ብዙውን
    0.38
    lema
    0.37
     आयकर
    0.37
    Act Density 0.000%

    No Known Activations