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

    Neuronpedia

    INDEX
    Explanations

    more

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Wor
    -0.07
     getText
    -0.07
    _dict
    -0.06
     outgoing
    -0.06
    (cors
    -0.06
    dp
    -0.06
     preset
    -0.06
    .getTotal
    -0.06
    _min
    -0.06
     Arts
    -0.06
    POSITIVE LOGITS
     PSA
    0.07
    placements
    0.07
    mina
    0.07
    ��取
    0.07
    }->{
    0.06
    .|
    0.06
     Singles
    0.06
     și
    0.06
     Vij
    0.06
     CLIIIK
    0.06
    Act Density 0.013%

    No Known Activations