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

    Neuronpedia

    INDEX
    Explanations

    generating prompts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ों
    1.95
    েও
    1.95
    ه
    1.92
    ات
    1.82
    s
    1.66
    আব
    1.65
    де
    1.59
    ে
    1.58
    मध्यप्रदेश
    1.57
    ामध्ये
    1.56
    POSITIVE LOGITS
    }));
    1.36
     stanowi
    1.33
    ../
    1.24
     Quellen
    1.22
     itibaren
    1.22
    ০০
    1.21
    }$)
    1.20
    }$$
    1.20
    }$
    1.19
    ция
    1.19
    Act Density 0.033%

    No Known Activations