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

    Neuronpedia

    INDEX
    Explanations

    group of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .conditions
    -0.07
     SHR
    -0.06
    LF
    -0.06
     ENERGY
    -0.06
     Lang
    -0.06
    _name
    -0.06
    ([]);↵↵
    -0.06
     LR
    -0.06
    -To
    -0.06
     CALLBACK
    -0.06
    POSITIVE LOGITS
     asses
    0.06
    .coin
    0.06
     crap
    0.06
    ressive
    0.06
     amat
    0.06
    unakan
    0.06
    ратно
    0.06
    roots
    0.06
     disg
    0.06
     há
    0.06
    Act Density 0.031%

    No Known Activations