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

    Neuronpedia

    INDEX
    Explanations

    demonstration of actions and objects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Carlo
    0.57
    種類の
    0.52
     dilwale
    0.50
     سوری
    0.50
    Ideal
    0.50
    Vers
    0.48
    Uz
    0.48
    Bear
    0.48
    SpawnEntry
    0.47
    Medieval
    0.46
    POSITIVE LOGITS
    it
    0.53
     {
    0.48
     Retail
    0.46
     sandwiched
    0.44
     \
    0.44
    0.43
    綬
    0.42
     Quantum
    0.42
     $\
    0.42
     double
    0.42
    Act Density 0.004%

    No Known Activations