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

    Neuronpedia

    INDEX
    Explanations

    Instructions and explanations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     бан
    -0.07
    AME
    -0.07
     mans
    -0.07
     larg
    -0.07
     يوم
    -0.07
     misunderstand
    -0.06
     elephants
    -0.06
    .docs
    -0.06
    必要
    -0.06
    oft
    -0.06
    POSITIVE LOGITS
    еления
    0.06
     entonces
    0.06
    нила
    0.06
    .Check
    0.06
    ,st
    0.06
    ับสน
    0.06
    /fs
    0.06
    _cf
    0.06
    .deepEqual
    0.06
     Clothing
    0.06
    Act Density 0.065%

    No Known Activations