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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    itzerland
    -0.06
    ーパー
    -0.06
    sar
    -0.06
    ♀
    -0.06
     counselling
    -0.06
    Tel
    -0.06
     pygame
    -0.06
    /rest
    -0.06
    üyor
    -0.06
     accus
    -0.06
    POSITIVE LOGITS
     qualifiers
    0.07
    .at
    0.07
     jj
    0.06
    ILITIES
    0.06
     BIND
    0.06
     proposes
    0.06
    .indent
    0.06
    ustom
    0.06
    .forEach
    0.06
     αστ
    0.06
    Act Density 0.023%

    No Known Activations