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

    Neuronpedia

    INDEX
    Explanations

    optimal long storagesimulate outdoor running

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     approval
    0.48
     automl
    0.45
     wherein
    0.42
     tertiary
    0.42
     stealth
    0.41
     term
    0.40
     across
    0.40
     clause
    0.40
     attached
    0.40
     revocation
    0.39
    POSITIVE LOGITS
     опреде
    0.44
     иссле
    0.42
     اعز
    0.41
     представления
    0.41
    нами
    0.40
    azzi
    0.40
     releases
    0.39
    Katherine
    0.39
    useppe
    0.38
     Katherine
    0.38
    Act Density 0.000%

    No Known Activations