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

    Neuronpedia

    INDEX
    Explanations

    emergency service helplines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ="))
    0.39
    ⺈
    0.38
    嬠
    0.37
    <unused718>
    0.37
    <unused698>
    0.36
    琕
    0.36
    ﹙
    0.36
    URNIZ
    0.36
     beerCount
    0.36
    䔋
    0.35
    POSITIVE LOGITS
    0.48
    。
    0.40
    "
    0.37
     in
    0.37
    ,"
    0.37
    ."
    0.35
    ".
    0.34
    ",
    0.34
    ,
    0.34
     "
    0.33
    Act Density 0.023%

    No Known Activations