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

    Neuronpedia

    INDEX
    Explanations

    bash code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cope
    -0.07
     control
    -0.07
    .");
    -0.07
     PK
    -0.07
    romatic
    -0.07
     �
    -0.06
    _DETAIL
    -0.06
    omedical
    -0.06
    19
    -0.06
     toured
    -0.06
    POSITIVE LOGITS
     eagerly
    0.06
    ，我
    0.06
    аци
    0.06
    -close
    0.06
     wishing
    0.06
    ening
    0.06
    _legal
    0.06
     hall
    0.06
    heten
    0.06
    gel
    0.06
    Act Density 0.005%

    No Known Activations