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

    Neuronpedia

    INDEX
    Explanations

    print the solution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     clashed
    0.80
    𝐚
    0.78
     Î
    0.78
     Ï
    0.76
    ราะห์
    0.76
     havoc
    0.75
     pauses
    0.75
    埝
    0.74
     Celtics
    0.74
     assertFalse
    0.73
    POSITIVE LOGITS
    is
    0.75
    т
    0.69
    տ
    0.66
    StrictMode
    0.65
    ณิต
    0.64
    また
    0.64
    chlor
    0.64
    sentence
    0.63
    HashTable
    0.63
    denominator
    0.63
    Act Density 0.000%

    No Known Activations