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

    Neuronpedia

    INDEX
    Explanations

    However

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ständ
    -0.07
     sobie
    -0.07
    -values
    -0.07
    bourg
    -0.06
     NSS
    -0.06
     biases
    -0.06
     Issues
    -0.06
    peat
    -0.06
    Assertion
    -0.06
    iê
    -0.06
    POSITIVE LOGITS
    .are
    0.06
    子
    0.06
     shack
    0.06
     portraits
    0.06
    RegularExpression
    0.06
     portals
    0.06
    .</
    0.06
    .mov
    0.06
     receiver
    0.06
    Correction
    0.06
    Act Density 0.037%

    No Known Activations