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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ότητα
    -0.07
    ControlItem
    -0.07
    _servers
    -0.06
     enerj
    -0.06
     viral
    -0.06
    _Method
    -0.06
    _iter
    -0.06
     Cer
    -0.06
     domains
    -0.06
     krev
    -0.06
    POSITIVE LOGITS
    ladım
    0.06
    pdb
    0.06
    귀
    0.06
     Ard
    0.06
     keş
    0.06
    PC
    0.06
    辺
    0.06
    アル
    0.06
    _AX
    0.06
    gzip
    0.06
    Act Density 0.000%

    No Known Activations