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

    Neuronpedia

    INDEX
    Explanations

    Python code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Meer
    0.38
    to
    0.36
    ২
    0.36
     Lees
    0.34
    ami
    0.34
     Entomology
    0.34
    is
    0.33
    cup
    0.33
    operatively
    0.33
    2
    0.33
    POSITIVE LOGITS
    ،
    0.40
     ،
    0.40
     불구하고
    0.39
     stipend
    0.38
    度和
    0.36
     diverg
    0.36
     وأن
    0.36
    ד
    0.36
    на
    0.35
     언제
    0.35
    Act Density 0.000%

    No Known Activations