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

    Neuronpedia

    INDEX
    Explanations

    dependencies and imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CLUS
    0.39
    विष
    0.39
    Compl
    0.38
     plabic
    0.38
    Compounds
    0.38
    㞓
    0.38
    苷
    0.37
    Composition
    0.37
    तुर
    0.36
     gameOver
    0.36
    POSITIVE LOGITS
    ید
    0.53
     T
    0.47
    ia
    0.47
    о
    0.47
    v
    0.46
    го
    0.46
    а
    0.46
    io
    0.45
     K
    0.45
    ow
    0.44
    Act Density 0.001%

    No Known Activations