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

    Neuronpedia

    INDEX
    Explanations

    database entries/cases

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ν
    -0.07
     cameo
    -0.07
    uploader
    -0.07
     víde
    -0.06
     bowel
    -0.06
    ищ
    -0.06
     Ты
    -0.06
     品
    -0.06
     psycopg
    -0.06
     prest
    -0.06
    POSITIVE LOGITS
    	char
    0.06
    .script
    0.06
     Ang
    0.06
    ../../../
    0.06
    ,st
    0.06
    _parent
    0.06
     TESTING
    0.06
    hack
    0.06
    prove
    0.06
    .lng
    0.06
    Act Density 0.029%

    No Known Activations