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

    Neuronpedia

    INDEX
    Explanations

    start of actions or processes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ิร์
    0.47
    nú
    0.43
    jmath
    0.40
    ವರೆ
    0.39
    áil
    0.38
    ulf
    0.38
     इनटू
    0.38
     எண்ணிக்கை
    0.37
     out
    0.37
    codename
    0.37
    POSITIVE LOGITS
     eating
    0.42
     জিজ্ঞ
    0.40
     माँग
    0.40
     faveur
    0.38
    eating
    0.37
    舫
    0.37
     U
    0.36
     Eating
    0.36
    త్య
    0.36
     martini
    0.36
    Act Density 0.000%

    No Known Activations