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

    Neuronpedia

    INDEX
    Explanations

    pastebin links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     horr
    0.32
    स्परिक
    0.28
     castration
    0.27
     ochrony
    0.26
    らう
    0.26
     vacuo
    0.26
     murdering
    0.26
    佉
    0.26
     solucionar
    0.26
     Versorgung
    0.26
    POSITIVE LOGITS
    _
    0.36
    -
    0.34
    peek
    0.33
    0.33
    un
    0.32
    ay
    0.32
    yn
    0.31
     [
    0.31
    ↵
    0.31
    current
    0.31
    Act Density 0.068%

    No Known Activations