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

    Neuronpedia

    INDEX
    Explanations

    code comments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     discipline
    -0.07
     Blackhawks
    -0.07
    INTEGER
    -0.07
    (',')↵
    -0.06
     moduleId
    -0.06
     Ding
    -0.06
     Armor
    -0.06
    ibility
    -0.06
     Miz
    -0.06
    POSITE
    -0.06
    POSITIVE LOGITS
     навк
    0.06
     prost
    0.06
    accept
    0.06
    обра�
    0.06
    enna
    0.06
    appro
    0.06
     accept
    0.06
     urllib
    0.06
    ωσε
    0.06
     Abel
    0.06
    Act Density 0.027%

    No Known Activations