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

    Neuronpedia

    INDEX
    Explanations

    )}

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uga
    -0.09
    liy
    -0.09
    atiin
    -0.08
    abus
    -0.08
    atoare
    -0.08
    ablanca
    -0.08
    اطة
    -0.08
    appro
    -0.08
    πα
    -0.08
     prò
    -0.08
    POSITIVE LOGITS
    _{\
    0.14
    {\
    0.12
     \
    0.12
    _\
    0.12
    }$
    0.12
    \,
    0.11
    [\
    0.11
    (\
    0.11
    =\
    0.11
    $↵
    0.10
    Act Density 0.011%

    No Known Activations