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

    Neuronpedia

    INDEX
    Explanations

    space followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cathodic
    0.42
     cad
    0.41
    onc
    0.41
     obtaining
    0.40
     farms
    0.40
    ریہ
    0.40
     obtains
    0.39
     tenor
    0.38
    central
    0.38
     onc
    0.38
    POSITIVE LOGITS
    Toggle
    0.51
    ซิต
    0.43
    ập
    0.42
    하게
    0.41
    †
    0.39
    Tod
    0.38
    ünftig
    0.38
    }];
    0.37
    Menu
    0.37
    हायला
    0.37
    Act Density 0.000%

    No Known Activations