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

    Neuronpedia

    INDEX
    Explanations

    machine learning and related fields

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Faucet
    0.61
    Deja
    0.56
    Exponential
    0.54
    Decrement
    0.53
    Deprecated
    0.53
     hoera
    0.53
    Infl
    0.53
    Additive
    0.53
     Sparse
    0.52
    IfNeeded
    0.51
    POSITIVE LOGITS
     justice
    1.03
     literacy
    1.00
     science
    0.99
     intelligence
    0.91
    justice
    0.89
     sciences
    0.89
     stewardship
    0.87
     management
    0.85
     education
    0.85
     जस्टिस
    0.83
    Act Density 0.468%

    No Known Activations