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

    Neuronpedia

    INDEX
    Explanations

    split into equal pieces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    i
    0.47
     yattha
    0.46
     Erickson
    0.45
     unten
    0.45
     kriter
    0.44
    撹
    0.44
     vudd
    0.43
     Merlin
    0.43
    过去的
    0.42
     Claire
    0.42
    POSITIVE LOGITS
     particles
    0.46
    あの
    0.46
    3
    0.46
    じ
    0.45
    ものが
    0.44
    événement
    0.43
     age
    0.43
    κες
    0.43
    サイズ
    0.42
    seas
    0.42
    Act Density 0.004%

    No Known Activations