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

    Neuronpedia

    INDEX
    Explanations

    code characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     этот
    -0.07
    peer
    -0.07
    ozy
    -0.06
     mtx
    -0.06
     CPP
    -0.06
    ftime
    -0.06
    .ejb
    -0.06
    _chain
    -0.06
    Prog
    -0.06
    -unit
    -0.06
    POSITIVE LOGITS
     unaffected
    0.07
    خی
    0.07
     deeds
    0.06
    .median
    0.06
    γκα
    0.06
    305
    0.06
    лага
    0.06
    _PERMISSION
    0.06
    888
    0.06
    _EQ
    0.06
    Act Density 0.122%

    No Known Activations