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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    第二批
    -0.08
    -ln
    -0.07
    짧
    -0.07
     zip
    -0.07
     ./
    -0.07
     !");↵
    -0.07
    $link
    -0.07
    .dy
    -0.07
     đẩ
    -0.07
    ."+
    -0.07
    POSITIVE LOGITS
     Coding
    0.08
     scattered
    0.08
    倭
    0.07
    奢侈
    0.07
    vious
    0.07
    _CLEAR
    0.07
    orum
    0.07
    licated
    0.07
     coding
    0.07
     nur
    0.07
    Act Density 0.012%

    No Known Activations