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

    Neuronpedia

    INDEX
    Explanations

    Fantasy texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cram
    -0.07
     bars
    -0.06
     thousands
    -0.06
     weil
    -0.06
    	db
    -0.06
    static
    -0.06
    ura
    -0.06
    imating
    -0.06
     revis
    -0.06
     Veronica
    -0.06
    POSITIVE LOGITS
    Swagger
    0.07
    як
    0.07
     Kag
    0.06
    _COMPARE
    0.06
     }}}
    0.06
    }}}
    0.06
    .getOwnProperty
    0.06
    Jackson
    0.06
    _ANS
    0.06
     область
    0.06
    Act Density 0.009%

    No Known Activations