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

    Neuronpedia

    INDEX
    Explanations

    return

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     perg
    -0.07
     sowie
    -0.06
    idenav
    -0.06
     جهت
    -0.06
     Clintons
    -0.06
     быть
    -0.06
     Пред
    -0.06
     слов
    -0.06
     ´
    -0.06
    ']]
    -0.06
    POSITIVE LOGITS
    riet
    0.07
     Griffith
    0.07
     ranking
    0.07
     Cah
    0.06
    届
    0.06
    turn
    0.06
     //////
    0.06
     Carnegie
    0.06
    리카
    0.06
     kinetics
    0.06
    Act Density 0.005%

    No Known Activations