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

    Neuronpedia

    INDEX
    Explanations

    component declarations and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Tissue
    0.79
    ACTIVITY
    0.75
     ACTIVITY
    0.74
    怿
    0.74
     ponad
    0.73
    citet
    0.73
    Aaron
    0.71
    Highway
    0.71
     jogar
    0.71
     نتیجه
    0.70
    POSITIVE LOGITS
     providers
    1.24
    providers
    1.21
    imports
    1.12
     Providers
    1.12
     imports
    1.11
    Providers
    1.03
     exports
    1.03
     declarations
    1.01
    bootstrap
    0.92
     bootstrap
    0.91
    Act Density 0.006%

    No Known Activations