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

    Neuronpedia

    INDEX
    Explanations

    evaluate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -part
    -0.07
    博物
    -0.07
    Prop
    -0.07
     conglomer
    -0.06
    Clark
    -0.06
    .preference
    -0.06
     Beijing
    -0.06
     Zak
    -0.06
     expertise
    -0.06
     Х
    -0.06
    POSITIVE LOGITS
    ?(
    0.07
    .on
    0.07
    href
    0.07
     swings
    0.07
     ре
    0.07
    ewood
    0.07
    ?(:
    0.06
    ΙΟ
    0.06
    (attrs
    0.06
    WORD
    0.06
    Act Density 0.013%

    No Known Activations