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

    Neuronpedia

    INDEX
    Explanations

    code and programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iseum
    -0.07
    ]++;↵
    -0.06
     copyrighted
    -0.06
    -radio
    -0.06
    atre
    -0.06
    _ADAPTER
    -0.06
     thí
    -0.06
    thinking
    -0.05
     зел
    -0.05
    agrid
    -0.05
    POSITIVE LOGITS
     dost
    0.07
     closures
    0.07
    RN
    0.07
     phrase
    0.07
    natal
    0.06
    ائرة
    0.06
     contends
    0.06
    ifle
    0.06
     možné
    0.06
    (
↵
    0.06
    Act Density 0.014%

    No Known Activations