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

    Neuronpedia

    INDEX
    Explanations

    Balls/nuts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ytic
    -0.07
    /avatar
    -0.07
    pecific
    -0.07
    霉
    -0.07
    étr
    -0.07
    他们都
    -0.06
    ismic
    -0.06
    和地区
    -0.06
    евич
    -0.06
    /'↵
    -0.06
    POSITIVE LOGITS
    Ͽ
    0.07
     ngăn
    0.07
     dü
    0.07
     inflate
    0.07
    🇦
    0.07
    _KEEP
    0.07
     CPUs
    0.07
    .assertIs
    0.07
     sparkling
    0.06
    ⚖
    0.06
    Act Density 0.005%

    No Known Activations