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

    Neuronpedia

    INDEX
    Explanations

    say this

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Yale
    -0.08
    requires
    -0.07
    ﴿
    -0.07
     Graduate
    -0.07
     decrypt
    -0.07
     tienes
    -0.07
    .SceneManagement
    -0.07
     Kaplan
    -0.06
    ект
    -0.06
    itura
    -0.06
    POSITIVE LOGITS
    (fm
    0.07
    .realpath
    0.07
    -num
    0.07
    .toggle
    0.07
    …"↵↵
    0.06
    %p
    0.06
     additions
    0.06
    ".↵
    0.06
    .nr
    0.06
    وحدة
    0.06
    Act Density 0.001%

    No Known Activations