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

    Neuronpedia

    INDEX
    Explanations

    software compatibility

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ²,
    1.14
    ).
    1.12
    ,
    1.11
    2
    0.99
    ’,
    0.98
    ování
    0.98
    ’;
    0.98
    }.
    0.98
    ,'
    0.96
    ,=
    0.95
    POSITIVE LOGITS
    ro
    1.23
    ר
    1.22
    ۰
    1.19
    il
    1.16
     Compatibility
    1.16
    ل
    1.13
    ด
    1.12
     for
    1.07
    at
    1.06
    다
    1.06
    Act Density 0.033%

    No Known Activations