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

    Neuronpedia

    INDEX
    Explanations

    mathematical exponents and operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     proactive
    0.89
     reimag
    0.88
     expertly
    0.87
     HVAC
    0.86
     lounge
    0.85
     Salesforce
    0.83
     SaaS
    0.83
     empath
    0.82
     befri
    0.81
     speaks
    0.80
    POSITIVE LOGITS
    ^{-
    1.26
    ^(-
    1.11
    ^{-\
    1.11
    ^{-(
    0.98
    ^{
    0.95
    }^{-
    0.94
    Inverse
    0.94
    Hasil
    0.88
    sqrt
    0.85
    Normalization
    0.85
    Act Density 0.257%

    No Known Activations