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

    Neuronpedia

    INDEX
    Explanations

    foreign language identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    在哪里
    0.35
     in
    0.33
    IPE
    0.33
    <ul>
    0.31
    া
    0.30
    ipe
    0.30
    <unused2138>
    0.30
    openg
    0.30
    áy
    0.30
    гри
    0.29
    POSITIVE LOGITS
    issements
    0.38
    Tidak
    0.36
    雦
    0.35
     comunità
    0.34
     হইতেছিল
    0.34
     druge
    0.34
     ljubav
    0.34
     inimes
    0.33
    افظ
    0.33
     wanita
    0.33
    Act Density 0.000%

    No Known Activations