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

    Neuronpedia

    INDEX
    Explanations

    code comments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     oat
    -0.07
    igsaw
    -0.07
     نار
    -0.06
     sua
    -0.06
    =""↵
    -0.06
     yerleş
    -0.06
     Parish
    -0.06
    _ESCAPE
    -0.06
    '";
↵
    -0.06
     каль
    -0.06
    POSITIVE LOGITS
     integrate
    0.07
    VM
    0.07
     ABD
    0.06
    .Update
    0.06
     registering
    0.06
    กำหนด
    0.06
    (weights
    0.06
    emiz
    0.06
    ALLENG
    0.06
     fantastic
    0.06
    Act Density 0.001%

    No Known Activations