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

    Neuronpedia

    INDEX
    Explanations

    strings of strong profanity, especially the f-word.

    oai_token-act-pair · gemini-2.0-flash

    angry quotes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    afone
    -0.71
    fjspx
    -0.71
     تضيفلها
    -0.70
    enterOuterAlt
    -0.67
     kaarangay
    -0.65
     mergeFrom
    -0.65
    SharedCtor
    -0.64
    sizeCache
    -0.62
     kasarigan
    -0.61
    nities
    -0.60
    POSITIVE LOGITS
     venons
    0.62
     voulons
    0.49
    GPL
    0.48
     industriel
    0.46
     necesitan
    0.46
     defiant
    0.45
     blijven
    0.45
    耳
    0.44
    帖最后由
    0.44
     ferons
    0.44
    Act Density 1.644%

    No Known Activations