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

    Neuronpedia

    INDEX
    Explanations

    java libraries and imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     emptying
    0.85
     Herring
    0.84
     unsatisfied
    0.79
     adjourned
    0.79
     emptied
    0.77
     pasted
    0.77
    0.76
     pasting
    0.76
    rimazole
    0.75
     Andy
    0.75
    POSITIVE LOGITS
    badlogic
    0.82
    fasterxml
    0.81
    Utilities
    0.75
    System
    0.75
    IOException
    0.68
     দ্বীপ
    0.67
    util
    0.66
    Common
    0.65
    Custom
    0.65
    java
    0.65
    Act Density 0.000%

    No Known Activations