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

    Neuronpedia

    INDEX
    Explanations

    making limits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Wenn
    0.44
    你
    0.42
    Expert
    0.40
    Physics
    0.40
    Thermo
    0.40
    Selling
    0.40
    You
    0.39
    Sie
    0.39
    Implicit
    0.39
    Seeking
    0.39
    POSITIVE LOGITS
    碜
    0.39
     cetera
    0.39
    uidor
    0.38
    ursor
    0.37
    ceaux
    0.36
    esehen
    0.36
     Seen
    0.36
     Origins
    0.36
     Objects
    0.36
     Hence
    0.35
    Act Density 0.000%

    No Known Activations