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

    Neuronpedia

    INDEX
    Explanations

    personal struggles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    high
    -0.07
    METHOD
    -0.07
    zc
    -0.06
     第三
    -0.06
    เจ
    -0.06
    antor
    -0.06
     certain
    -0.06
     competing
    -0.06
    b
    -0.06
    II
    -0.06
    POSITIVE LOGITS
     nově
    0.07
     现
    0.07
    .qty
    0.06
    .Image
    0.06
    만원입니다
    0.06
     ance
    0.06
     kit
    0.06
     �
    0.06
    /assert
    0.06
    ertest
    0.06
    Act Density 0.243%

    No Known Activations