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

    Neuronpedia

    INDEX
    Explanations

    System

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    verg
    0.79
     Dot
    0.74
    Dot
    0.74
    Grove
    0.74
    ⅝
    0.61
     Grove
    0.61
    dot
    0.61
    Echo
    0.60
     Recall
    0.60
    ဆင့်
    0.60
    POSITIVE LOGITS
    ারে
    0.73
     purifier
    0.71
     solvent
    0.70
     ligation
    0.70
     legends
    0.69
     matr
    0.69
     antioxidant
    0.68
    meno
    0.68
     maid
    0.68
     astronomer
    0.68
    Act Density 0.002%

    No Known Activations