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

    Neuronpedia

    INDEX
    Explanations

    nasa science links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     $\{
    0.44
     ${({
    0.42
     \<
    0.42
    ඳු
    0.41
     quantitatively
    0.40
     (…)
    0.38
     quadr
    0.37
     क्वांट
    0.37
    Chelsea
    0.37
     nbsp
    0.36
    POSITIVE LOGITS
    hept
    0.50
    ⋮
    0.43
    \{{}\
    0.43
    Leftrightarrow
    0.40
    left
    0.39
    [{}\
    0.39
    =-
    0.37
    +...+
    0.37
     digested
    0.36
    0.36
    Act Density 0.001%

    No Known Activations