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

    Neuronpedia

    INDEX
    Explanations

    sm

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Bounds
    -0.07
    -inverse
    -0.07
    ”
    -0.07
    igue
    -0.06
    きた
    -0.06
    τού
    -0.06
    params
    -0.06
    ‐
    -0.06
    (optarg
    -0.06
     Gospel
    -0.06
    POSITIVE LOGITS
     sm
    0.33
    	sm
    0.07
    htmlspecialchars
    0.07
    (sm
    0.06
     desires
    0.06
     sme
    0.06
     mir
    0.06
     shitty
    0.06
    unately
    0.06
     iletişim
    0.06
    Act Density 0.003%

    No Known Activations