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

    Neuronpedia

    INDEX
    Explanations

    content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     decreasing
    -0.06
     generator
    -0.06
     decade
    -0.06
     spontaneously
    -0.06
     researcher
    -0.06
    cano
    -0.06
     hostility
    -0.06
    ehicle
    -0.06
     تكييف
    -0.06
     tedav
    -0.06
    POSITIVE LOGITS
     Betting
    0.07
     ';
↵
    0.07
     desserts
    0.06
     Saskatchewan
    0.06
    ним
    0.06
    (accounts
    0.06
     ^.
    0.06
    /@
    0.06
    舞
    0.06
    !.
    0.06
    Act Density 0.010%

    No Known Activations