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

    Neuronpedia

    INDEX
    Explanations

    online poker

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ('#
    0.48
     instantiated
    0.48
     monotonically
    0.46
     институ
    0.45
     apoptotic
    0.44
    apeti
    0.44
    𝙣
    0.43
    饗
    0.42
     cytotoxic
    0.42
     uncompromising
    0.42
    POSITIVE LOGITS
     will
    0.46
    äksi
    0.43
    isFile
    0.42
     Jason
    0.40
     Dale
    0.39
    will
    0.38
     Wayne
    0.38
     st
    0.38
     Synopsis
    0.37
     Victor
    0.37
    Act Density 0.013%

    No Known Activations