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

    Neuronpedia

    INDEX
    Explanations

    social media

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     week
    -0.07
    팎
    -0.07
    뜰
    -0.06
    Mom
    -0.06
    Big
    -0.06
     выход
    -0.06
    -Compatible
    -0.06
    犨
    -0.06
     bacon
    -0.06
     Utah
    -0.06
    POSITIVE LOGITS
    ⓩ
    0.08
     Ships
    0.07
    (Blueprint
    0.07
    -how
    0.07
    】【
    0.07
                         ↵
    0.07
    سقط
    0.07
    .destroy
    0.07
    '])){
↵
    0.07
     Angular
    0.07
    Act Density 0.001%

    No Known Activations