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

    Neuronpedia

    INDEX
    Explanations

    information and contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kleine
    0.39
     nuovamente
    0.38
     zusätzlichen
    0.37
     kleinen
    0.35
     esclusivamente
    0.35
     immediatamente
    0.35
     upravo
    0.33
     escuch
    0.32
     cuja
    0.32
     nouveaux
    0.32
    POSITIVE LOGITS
    <unused2130>
    0.37
    文件
    0.31
    0.31
    <unused2148>
    0.30
    бург
    0.29
    <unused2125>
    0.28
     ζωή
    0.28
    的文件
    0.27
    蛲
    0.27
     $,
    0.26
    Act Density 0.265%

    No Known Activations