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

    Neuronpedia

    INDEX
    Explanations

    war

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    賞
    -0.07
    azione
    -0.07
     rage
    -0.07
    rice
    -0.06
     incentives
    -0.06
     insurgents
    -0.06
     Rage
    -0.06
    .Some
    -0.06
     Friends
    -0.06
    frared
    -0.06
    POSITIVE LOGITS
    $client
    0.06
    (obj
    0.06
     lez
    0.06
    setIcon
    0.06
     Australians
    0.06
    (menu
    0.06
     anz
    0.06
    onomies
    0.06
    creens
    0.06
     Austin
    0.06
    Act Density 0.131%

    No Known Activations