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

    Neuronpedia

    INDEX
    Explanations

    src

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sens
    -0.08
     Dou
    -0.07
     plung
    -0.07
     areas
    -0.07
     ремонт
    -0.07
     Điều
    -0.06
    etros
    -0.06
     Damien
    -0.06
    preced
    -0.06
     Att
    -0.06
    POSITIVE LOGITS
    coding
    0.07
    十二
    0.07
    _GL
    0.06
    xEC
    0.06
     PARTICULAR
    0.06
    *',
    0.06
    Beauty
    0.06
     �
    0.06
    =#{
    0.06
    CREATE
    0.06
    Act Density 0.006%

    No Known Activations