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

    Neuronpedia

    INDEX
    Explanations

    testing, verification, technical requirements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     minecraft
    0.97
     oauth
    0.89
     endGame
    0.88
     billionaires
    0.86
     scammers
    0.85
     xgboost
    0.84
     billionaire
    0.83
     nigh
    0.83
     rightfully
    0.83
     Kickstarter
    0.83
    POSITIVE LOGITS
    Input
    0.76
    Timing
    0.75
    Flow
    0.73
    Block
    0.70
    Allocation
    0.68
    קו
    0.67
     Flow
    0.66
    Inputs
    0.66
    Output
    0.66
     Timing
    0.65
    Act Density 0.089%

    No Known Activations