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

    Neuronpedia

    INDEX
    Explanations

    release versions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     হইলেই
    0.42
    滏
    0.40
    िसिटी
    0.39
    嗳
    0.38
     proliferative
    0.38
    iputi
    0.38
     exfoliating
    0.38
     ganglion
    0.37
     chromospheric
    0.37
     %>',
    0.37
    POSITIVE LOGITS
    RELEASE
    0.47
    SE
    0.43
     RELEASE
    0.43
    Release
    0.41
     release
    0.40
    BA
    0.40
    SED
    0.39
    IS
    0.39
    M
    0.39
     Release
    0.38
    Act Density 0.001%

    No Known Activations