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

    Neuronpedia

    INDEX
    Explanations

    html tags and structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.38
    Starting
    0.34
    Hig
    0.34
    Infer
    0.33
    Nation
    0.32
    Inst
    0.31
    Ident
    0.31
    </h1>
    0.31
    Observable
    0.31
    Connected
    0.31
    POSITIVE LOGITS
    href
    0.37
    boldsymbol
    0.36
    rceil
    0.35
    ೆಂದು
    0.35
    multicolumn
    0.35
     />
    0.34
    quot
    0.34
    ://
    0.33
    raquo
    0.33
    mathscr
    0.33
    Act Density 0.062%

    No Known Activations