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

    Neuronpedia

    INDEX
    Explanations

    lists, bullet points, and specific entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    }$
    1.38
    Ре
    1.38
    }$,
    1.30
    }"
    1.26
    に
    1.18
    éristique
    1.16
     речь
    1.14
    У
    1.12
    }^{\
    1.11
    у
    1.08
    POSITIVE LOGITS
    ബരിമല
    1.17
    ið
    1.15
    agad
    1.14
    klar
    1.14
    (../
    1.13
     setSelected
    1.13
    几何
    1.12
    jTextField
    1.10
    tional
    1.10
    kie
    1.09
    Act Density 0.000%

    No Known Activations