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

    Neuronpedia

    INDEX
    Explanations

    code explanations and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    I
    1.36
    ،
    0.99
    ↵
    0.96
    t
    0.84
    </h3>
    0.83
    ことを
    0.82
        
    0.81
     I
    0.79
     at
    0.79
     '.
    0.79
    POSITIVE LOGITS
    ين
    1.26
    ul
    1.20
    ва
    1.18
    م
    1.16
    ви
    1.06
    К
    1.05
    at
    1.04
    са
    1.03
    на
    1.02
    اك
    1.02
    Act Density 0.216%

    No Known Activations