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

    Neuronpedia

    INDEX
    Explanations

    Numbers and dates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ailure
    -0.08
     stif
    -0.07
     domingo
    -0.07
     Census
    -0.06
    642
    -0.06
    τρα
    -0.06
     openly
    -0.06
    _credentials
    -0.06
    	new
    -0.06
    ौट
    -0.06
    POSITIVE LOGITS
    .isAdmin
    0.07
    .loading
    0.07
     buried
    0.06
     shakes
    0.06
    ॉप
    0.06
    Ă
    0.06
    .youtube
    0.06
    .features
    0.06
     skips
    0.06
    terrain
    0.06
    Act Density 0.033%

    No Known Activations