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

    Neuronpedia

    INDEX
    Explanations

    punctuation and string tokens

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _dc
    -0.07
     conjug
    -0.07
    /be
    -0.06
    Devices
    -0.06
    vido
    -0.06
    _role
    -0.06
    _OUTPUT
    -0.06
     k
    -0.06
    	password
    -0.06
     кап
    -0.06
    POSITIVE LOGITS
     UIViewController
    0.07
     Під
    0.07
     Vaults
    0.07
     cestu
    0.06
    _layers
    0.06
     notre
    0.06
    ."[
    0.06
    .Sh
    0.06
     "[
    0.06
    么
    0.06
    Act Density 0.191%

    No Known Activations