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

    Neuronpedia

    INDEX
    Explanations

    Technical contexts

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    1
    0.95
    elerde
    0.90
    !“
    0.89
    9
    0.88
    8
    0.88
    MCs
    0.88
    4
    0.85
    7
    0.85
     compiling
    0.84
    ?“
    0.83
    POSITIVE LOGITS
    Up
    0.73
    ณ์
    0.72
    Ind
    0.72
    Industry
    0.72
    И
    0.72
    pain
    0.72
    បាន
    0.71
    點
    0.69
    点
    0.69
    া
    0.69
    Act Density 0.000%

    No Known Activations