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

    Neuronpedia

    INDEX
    Explanations

    URLs, code, biological terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mesas
    0.42
    frameNStart
    0.40
    ニャ
    0.38
    েনের
    0.37
    व्हाण
    0.37
    ✥
    0.37
    SEVERE
    0.36
    ijdens
    0.36
     tsar
    0.36
    Conte
    0.36
    POSITIVE LOGITS
    Bio
    0.42
    ষ্ঠ
    0.33
     Commonly
    0.33
     Ка
    0.32
    moil
    0.32
     commonly
    0.32
    Ви
    0.32
     પ
    0.32
    slaught
    0.32
    ’),
    0.32
    Act Density 0.000%

    No Known Activations