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

    Neuronpedia

    INDEX
    Explanations

    listing creative text formats

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     特
    0.39
    ปร
    0.36
    特
    0.35
    资产
    0.35
    effector
    0.34
    ارف
    0.34
    тропо
    0.33
     music
    0.33
    erkraut
    0.33
    接
    0.33
    POSITIVE LOGITS
     INCIDENTAL
    0.39
    RAP
    0.39
     tý
    0.39
    flor
    0.38
     retrospective
    0.37
     atentos
    0.37
     condu
    0.37
    dylib
    0.37
    DAILY
    0.36
     killing
    0.36
    Act Density 0.001%

    No Known Activations