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

    Neuronpedia

    INDEX
    Explanations

    Uncertain or disputed information

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    蕰
    -0.07
     Gör
    -0.07
     cud
    -0.07
    胭
    -0.07
    מכבי
    -0.07
    搋
    -0.07
    舷
    -0.07
    獍
    -0.07
    (days
    -0.07
     орган
    -0.07
    POSITIVE LOGITS
    .basic
    0.07
    assa
    0.07
    _persona
    0.07
    _dual
    0.06
    _version
    0.06
    hu
    0.06
    transition
    0.06
     favoured
    0.06
    っています
    0.06
    _exit
    0.06
    Act Density 0.125%

    No Known Activations