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

    Neuronpedia

    INDEX
    Explanations

    leave feeling, emerge destitute

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fresh
    0.38
    gp
    0.37
    ட்டா
    0.37
    expired
    0.36
    ště
    0.35
    sem
    0.35
    r
    0.35
    worn
    0.35
    bg
    0.34
    lama
    0.34
    POSITIVE LOGITS
    每次
    0.40
    也
    0.38
     sellest
    0.35
    ાવી
    0.35
    出去
    0.35
    ον
    0.34
     каждом
    0.34
     ontological
    0.34
    ાવ
    0.33
    лке
    0.33
    Act Density 0.003%

    No Known Activations