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

    Neuronpedia

    INDEX
    Explanations

    start of explanation titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Miscellaneous
    0.43
    Untitled
    0.41
    Or
    0.41
    Transparency
    0.39
     ಮಾತನಾಡ
    0.38
    ᱫ
    0.38
     periodistas
    0.37
    anyl
    0.36
    apour
    0.36
    ।.
    0.36
    POSITIVE LOGITS
     прави
    0.43
    ρίς
    0.41
    ７
    0.40
    rierte
    0.40
     step
    0.39
     방법
    0.39
     Closed
    0.38
     માત્ર
    0.38
    athu
    0.38
    𝑁
    0.38
    Act Density 0.036%

    No Known Activations