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

    Neuronpedia

    INDEX
    Explanations

    it

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ilma
    -0.08
     במידה
    -0.07
     Gaga
    -0.07
    �
    -0.07
    אפי
    -0.07
     gamm
    -0.07
    Scott
    -0.07
    MAC
    -0.07
    .ng
    -0.07
    恣
    -0.06
    POSITIVE LOGITS
    ")
↵
↵
    0.07
    平安
    0.07
    '}}>↵
    0.07
    ######↵
    0.07
    }'↵
    0.07
    delete
    0.07
    ']):
    0.07
    _row
    0.07
     стен
    0.07
    :white
    0.07
    Act Density 0.019%

    No Known Activations