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

    Neuronpedia

    INDEX
    Explanations

    opinions and biases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     IQueryable
    -0.07
     Incontri
    -0.07
     Injectable
    -0.07
     crim
    -0.07
    Compute
    -0.07
    밖에
    -0.07
    _Free
    -0.07
    Subviews
    -0.07
    Informe
    -0.07
     mare
    -0.07
    POSITIVE LOGITS
    力还是自
    0.07
     defs
    0.06
    -sales
    0.06
     Social
    0.06
    =index
    0.06
     repeating
    0.06
    🅖
    0.06
     writer
    0.06
     Classical
    0.06
    许多人
    0.06
    Act Density 0.033%

    No Known Activations