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

    Neuronpedia

    INDEX
    Explanations

    foreign characters

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    avail
    -0.08
     =
↵
    -0.07
     Sitting
    -0.07
    ारण
    -0.07
     též
    -0.06
    occus
    -0.06
    기관
    -0.06
    -ID
    -0.06
    IMA
    -0.06
    lož
    -0.06
    POSITIVE LOGITS
    ầ
    0.08
    (EX
    0.07
     bigotry
    0.07
    益
    0.06
     kadınlar
    0.06
    escort
    0.06
     contingent
    0.06
    .getElementsByClassName
    0.06
     السكان
    0.06
    仕事
    0.06
    Act Density 0.000%

    No Known Activations