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

    Neuronpedia

    INDEX
    Explanations

    closing parenthesis and operators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ।
    0.49
    anza
    0.44
    🦎
    0.44
    ная
    0.43
    🤽
    0.42
    ль
    0.41
    riften
    0.41
    жна
    0.40
     vignette
    0.40
    :}
    0.40
    POSITIVE LOGITS
    亾
    0.49
    வதும்
    0.46
     periods
    0.46
     Philippine
    0.45
     cung
    0.45
     Optimum
    0.44
    েরই
    0.43
     dě
    0.43
     Th
    0.43
     प्रे
    0.43
    Act Density 0.024%

    No Known Activations