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

    Neuronpedia

    INDEX
    Explanations

    terminal punctuation or list items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     jar
    0.55
     educ
    0.53
     caracter
    0.51
     დამ
    0.51
     amu
    0.51
     estab
    0.50
     photoc
    0.50
     tales
    0.48
     acclaim
    0.48
     imp
    0.47
    POSITIVE LOGITS
    িক্স
    0.50
     Miners
    0.46
    R
    0.44
    Hin
    0.43
     भूत
    0.42
     Ки
    0.42
    ával
    0.42
    Além
    0.42
     déplacement
    0.42
    ésre
    0.42
    Act Density 0.000%

    No Known Activations