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

    Neuronpedia

    INDEX
    Explanations

    writing instructions and related items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    on
    0.69
    at
    0.52
    ál
    0.51
    ע
    0.50
    0.48
    ╫
    0.45
    ו
    0.45
    숨
    0.45
     thấm
    0.45
    elijk
    0.45
    POSITIVE LOGITS
     verbatim
    0.53
     shippers
    0.52
    iodate
    0.50
     crystall
    0.50
     blueprint
    0.48
     buttermilk
    0.48
     identifying
    0.48
     watchful
    0.48
     doorbell
    0.47
     sickle
    0.44
    Act Density 0.000%

    No Known Activations