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

    Neuronpedia

    INDEX
    Explanations

    other

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     destroys
    -0.08
    ()↵
    -0.08
     migrated
    -0.07
    按
    -0.07
     traveled
    -0.07
    icultural
    -0.07
     Radius
    -0.07
     Hou
    -0.07
     rects
    -0.06
     gray
    -0.06
    POSITIVE LOGITS
     Inc
    0.06
    $str
    0.06
    .FindControl
    0.06
    프
    0.06
    todos
    0.06
    temp
    0.06
    대학
    0.06
     프로
    0.06
    adj
    0.05
    .opt
    0.05
    Act Density 0.000%

    No Known Activations