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

    Neuronpedia

    INDEX
    Explanations

    de

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ew
    -0.06
    青
    -0.06
    approve
    -0.05
     builder
    -0.05
    +A
    -0.05
    _COR
    -0.05
    yang
    -0.05
    PIPE
    -0.05
    requires
    -0.05
    yat
    -0.05
    POSITIVE LOGITS
    }',
    0.07
     můžete
    0.07
    배송
    0.07
     аром
    0.07
     SignUp
    0.07
     ру
    0.07
     notwithstanding
    0.07
    =[]↵
    0.07
     ninete
    0.07
    _integral
    0.06
    Act Density 0.088%

    No Known Activations