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

    Neuronpedia

    INDEX
    Explanations

    perspective, core, carefully

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    VarArgs
    0.54
     aggrieved
    0.49
    졀
    0.47
     Prothorax
    0.47
    ResBuffer
    0.47
     बिहार
    0.46
    বিহার
    0.46
     Paryayvachi
    0.45
     Caledonia
    0.45
     Giveen
    0.44
    POSITIVE LOGITS
    ما
    0.48
    О
    0.48
    mot
    0.45
    X
    0.44
    В
    0.44
    L
    0.44
    O
    0.44
    ومات
    0.43
    Ak
    0.43
    sterdam
    0.43
    Act Density 0.002%

    No Known Activations