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

    Neuronpedia

    INDEX
    Explanations

    Integrity and high standards

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _random
    -0.08
     быть
    -0.07
     も
    -0.07
     이어
    -0.07
     солн
    -0.06
    увалися
    -0.06
     입력
    -0.06
    istique
    -0.06
    minated
    -0.06
    cla
    -0.06
    POSITIVE LOGITS
     GPA
    0.07
    _BANK
    0.06
    .apple
    0.06
    .newBuilder
    0.06
     Osman
    0.06
    .Child
    0.06
    /
    0.06
    TIME
    0.06
    .MOUSE
    0.06
     iphone
    0.06
    Act Density 0.088%

    No Known Activations