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

    Neuronpedia

    INDEX
    Explanations

    personal experiences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _min
    -0.07
     Reduce
    -0.07
    ⇒
    -0.07
     Кор
    -0.07
     trab
    -0.07
    ]{
    -0.06
     transmitted
    -0.06
     neighbor
    -0.06
    >B
    -0.06
     abusing
    -0.06
    POSITIVE LOGITS
    .qq
    0.07
    稀缺
    0.07
    Collapse
    0.07
    _CSS
    0.07
     Thứ
    0.07
    褕
    0.07
    Interested
    0.07
    每一个人
    0.07
    (jPanel
    0.07
    ếc
    0.06
    Act Density 0.189%

    No Known Activations