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

    Neuronpedia

    INDEX
    Explanations

    NeurIPS

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Amit
    0.40
    носит
    0.39
     shortcuts
    0.39
    분이
    0.39
     اللغة
    0.39
     snelheid
    0.38
     rápido
    0.38
    분을
    0.38
     chutes
    0.38
    윳
    0.38
    POSITIVE LOGITS
    ob
    0.45
    oelectric
    0.42
    current
    0.39
    adh
    0.39
    dumb
    0.39
    us
    0.39
    aw
    0.39
    il
    0.39
    odh
    0.38
     Kik
    0.38
    Act Density 0.000%

    No Known Activations