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

    Neuronpedia

    INDEX
    Explanations

    Robinhood customer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iful
    1.12
     somme
    1.06
    oring
    1.04
     diff
    1.03
     kitten
    0.96
    ├──
    0.95
    amour
    0.95
    जुर्ग
    0.95
    颊
    0.94
    sister
    0.93
    POSITIVE LOGITS
     waveguides
    1.35
     SizedBox
    1.34
     Considerando
    1.32
     thence
    1.22
     nonequilibrium
    1.21
     maturities
    1.21
     علوم
    1.20
     Leit
    1.20
     अध्या
    1.19
    و
    1.17
    Act Density 0.002%

    No Known Activations