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

    Neuronpedia

    INDEX
    Explanations

    information and definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Etiam
    0.42
    述べ
    0.39
    சர
    0.38
    ermann
    0.37
    onter
    0.36
    imamente
    0.36
     একত্র
    0.35
     runner
    0.35
     laterally
    0.35
    娍
    0.34
    POSITIVE LOGITS
    writeByte
    0.43
    𝙰
    0.40
     제곱
    0.40
     Emulator
    0.39
     bitOp
    0.39
     baits
    0.38
     Kenyon
    0.38
    }^{+}=
    0.38
     Eugenia
    0.38
     jest
    0.37
    Act Density 0.001%

    No Known Activations