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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     proceeding
    -0.07
     DIV
    -0.06
    .bottomAnchor
    -0.06
     sunny
    -0.06
     Lem
    -0.06
     timelines
    -0.06
    ENTER
    -0.06
     common
    -0.06
    sticks
    -0.06
     Müdürlüğü
    -0.06
    POSITIVE LOGITS
    python
    0.07
    ?↵↵↵
    0.07
    liable
    0.07
    -approved
    0.06
     utiliz
    0.06
    uffer
    0.06
     FRA
    0.06
    ."↵↵↵
    0.06
    реб
    0.06
    iked
    0.06
    Act Density 0.001%

    No Known Activations