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

    Neuronpedia

    INDEX
    Explanations

    provide me with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    atile
    -0.09
    line
    -0.09
    ariant
    -0.09
    se
    -0.09
    er
    -0.09
    nge
    -0.09
    773
    -0.09
    ll
    -0.09
     fas
    -0.09
    mark
    -0.09
    POSITIVE LOGITS
    ander
    0.12
    /us
    0.11
    andering
    0.11
    etto
    0.10
     conspir
    0.09
    erk
    0.09
    chant
    0.09
    adow
    0.09
     culpa
    0.09
    eker
    0.09
    Act Density 0.041%

    No Known Activations