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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [idx
    -0.06
     /*
    -0.06
     inf
    -0.06
    .getP
    -0.06
     harassing
    -0.06
     kvinn
    -0.05
     jug
    -0.05
     Cr
    -0.05
     ridiculously
    -0.05
    Declared
    -0.05
    POSITIVE LOGITS
    _MR
    0.07
    يق
    0.07
    ему
    0.07
     círk
    0.06
    _stats
    0.06
    inned
    0.06
     النس
    0.06
     failures
    0.06
    UTERS
    0.06
     Comic
    0.06
    Act Density 0.019%

    No Known Activations