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

    Neuronpedia

    INDEX
    Explanations

    signup, vestibular, thermoplastic, jakarta

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    р
    2.95
    ্তন
    2.91
    ولي
    2.73
    !\!\
    2.68
    밥
    2.65
    ות
    2.57
    ]];
    2.55
    জন্য
    2.54
    hana
    2.52
    ">\
    2.47
    POSITIVE LOGITS
    ो
    3.75
    mét
    3.49
    ください
    3.17
    на
    3.10
    ন
    3.05
    deel
    3.05
    lished
    3.04
    О
    3.03
    ni
    2.99
    𝒏
    2.99
    Act Density 0.001%

    No Known Activations