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

    Neuronpedia

    INDEX
    Explanations

    URL encoding and XSS

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SIN
    0.37
    MUX
    0.36
    0.35
     SIN
    0.32
    OLO
    0.32
     COMPLEXES
    0.32
    OLOG
    0.31
     apopt
    0.31
     forage
    0.31
    iolipin
    0.31
    POSITIVE LOGITS
    apos
    0.32
    2
    0.32
    3
    0.32
     bolder
    0.32
     escaping
    0.32
     E
    0.32
     violating
    0.31
     Hector
    0.31
    7
    0.31
    ">
    0.31
    Act Density 0.023%

    No Known Activations