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

    Neuronpedia

    INDEX
    Explanations

    announcement text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ៖
    0.44
     tau
    0.40
     scaffold
    0.40
     dialogo
    0.40
     نز
    0.39
    𒅌
    0.39
    mtable
    0.39
    basecode
    0.39
     laissent
    0.38
    CFBundle
    0.38
    POSITIVE LOGITS
    air
    0.42
    做到
    0.40
    there
    0.38
    integr
    0.38
    Д
    0.37
    డ్
    0.37
    esso
    0.36
     هناك
    0.36
    sab
    0.36
    ம
    0.36
    Act Density 0.000%

    No Known Activations