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

    Neuronpedia

    INDEX
    Explanations

    questions and conditions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hug
    -0.06
    starter
    -0.06
    larg
    -0.06
     childish
    -0.06
     break
    -0.06
     localtime
    -0.06
    endoza
    -0.06
    spell
    -0.06
     Siege
    -0.06
    но
    -0.06
    POSITIVE LOGITS
     ден
    0.07
    éo
    0.07
     福
    0.07
    _IND
    0.07
     ح
    0.06
     cerr
    0.06
     triệu
    0.06
     inform
    0.06
    ному
    0.06
    Ann
    0.06
    Act Density 0.048%

    No Known Activations