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

    Neuronpedia

    INDEX
    Explanations

    Jokes and riddles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     BETWEEN
    -0.07
    떡
    -0.07
     lanc
    -0.07
     prefixes
    -0.07
    _agents
    -0.07
     abdom
    -0.07
    針
    -0.06
    כיון
    -0.06
     jus
    -0.06
    ())),↵
    -0.06
    POSITIVE LOGITS
     Kot
    0.07
    ony
    0.07
    owa
    0.07
    squeeze
    0.07
    .steps
    0.07
    ᛁ
    0.07
    0.06
    ="_
    0.06
     Kavanaugh
    0.06
    grey
    0.06
    Act Density 0.004%

    No Known Activations