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

    Neuronpedia

    INDEX
    Explanations

    small

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pregnant
    -0.07
    _two
    -0.06
    atology
    -0.06
    Tw
    -0.06
    á
    -0.06
     undergone
    -0.06
    .Command
    -0.06
    rand
    -0.06
    рь
    -0.06
    /logs
    -0.06
    POSITIVE LOGITS
    .Escape
    0.07
     insets
    0.06
    	iVar
    0.06
    177
    0.06
     globals
    0.06
    (vals
    0.06
    .OutputStream
    0.06
    582
    0.06
     incent
    0.06
     مواد
    0.06
    Act Density 0.023%

    No Known Activations