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

    Neuronpedia

    INDEX
    Explanations

    common English words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .argmax
    -0.07
    둥
    -0.07
    -क
    -0.06
     geil
    -0.06
     สามารถ
    -0.06
     늘
    -0.06
     @$_
    -0.06
     varieties
    -0.06
     dobré
    -0.06
    "))
    -0.06
    POSITIVE LOGITS
    terminal
    0.07
     extending
    0.07
    Wild
    0.07
    +
    0.06
    Include
    0.06
     tapping
    0.06
     neighborhoods
    0.06
    ’.
    0.06
    installed
    0.06
     |
    0.06
    Act Density 0.000%

    No Known Activations