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

    Neuronpedia

    INDEX
    Explanations

    introducing descriptive statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ologici
    0.25
     הער
    0.24
    acknow
    0.24
     Eing
    0.24
    legisl
    0.23
    git
    0.23
    iót
    0.23
     Архі
    0.23
     considere
    0.22
     Во
    0.22
    POSITIVE LOGITS
    าย
    0.25
    㽚
    0.25
     szcz
    0.23
     reversals
    0.23
     dizzy
    0.23
     ses
    0.23
     donate
    0.23
     robot
    0.22
     Pt
    0.22
     glared
    0.22
    Act Density 0.001%

    No Known Activations