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

    Neuronpedia

    INDEX
    Explanations

    lists with structure or enumeration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     plantations
    0.84
     standings
    0.75
     langs
    0.74
     trees
    0.74
     dignitaries
    0.74
     ant
    0.73
     potion
    0.72
     intrat
    0.68
     Trees
    0.66
     decorations
    0.66
    POSITIVE LOGITS
    So
    0.97
    ૂ
    0.96
    While
    0.92
    Так
    0.91
    However
    0.90
    Lorsque
    0.88
    Съ
    0.87
    Popular
    0.87
    Suppose
    0.86
    Disclosure
    0.86
    Act Density 0.001%

    No Known Activations