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

    Neuronpedia

    INDEX
    Explanations

    definitely followed by possibility or recommendation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ième
    1.26
     directo
    1.16
    рёх
    1.14
    )}
    1.07
     serem
    1.07
    o
    1.06
    ために
    1.05
     dismantled
    1.05
     EPR
    1.05
     quatre
    1.05
    POSITIVE LOGITS
    на
    1.77
    ాలు
    1.45
    ات
    1.41
    thane
    1.37
    एस
    1.34
    ą
    1.32
     hypersurfaces
    1.28
    ב
    1.28
    га
    1.27
    и
    1.27
    Act Density 0.005%

    No Known Activations