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

    Neuronpedia

    INDEX
    Explanations

    generating images or describing actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵
    0.43
    -
    0.38
    B
    0.36
    S
    0.36
    ;
    0.34
     Journal
    0.33
    }
    0.33
     ||
    0.33
    ↵↵
    0.32
     I
    0.32
    POSITIVE LOGITS
    segaretro
    0.46
     সময়
    0.43
    गमेंट
    0.39
    व्हाण
    0.38
    ंदरे
    0.38
    슴
    0.38
    dürü
    0.37
    чом
    0.36
     плани
    0.36
    𝙜
    0.36
    Act Density 0.002%

    No Known Activations