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

    Neuronpedia

    INDEX
    Explanations

    microscopic details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     resting
    0.41
     rested
    0.38
    ⎤
    0.37
    묘
    0.35
    夻
    0.34
    implement
    0.34
     молодой
    0.34
    jdField
    0.34
    сант
    0.34
    цій
    0.34
    POSITIVE LOGITS
    Mik
    0.43
     mik
    0.43
     Mik
    0.43
     Individual
    0.42
     Micro
    0.41
    微
    0.41
    Mic
    0.39
    Micro
    0.39
    哥
    0.38
     micro
    0.38
    Act Density 0.000%

    No Known Activations