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

    Neuronpedia

    INDEX
    Explanations

    specifications and approximate values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused1038>
    0.50
     bustling
    0.49
    <unused1130>
    0.49
     juxtaposition
    0.48
    सभी
    0.48
    𒊭
    0.47
     intitulé
    0.47
     :).
    0.47
    <unused519>
    0.46
    <unused989>
    0.46
    POSITIVE LOGITS
    HP
    0.44
    MF
    0.42
    近似
    0.41
    ：
    0.41
    ↵
    0.40
    RP
    0.40
    Minimum
    0.40
    TF
    0.40
    TP
    0.39
    DK
    0.39
    Act Density 0.001%

    No Known Activations