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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     DropDownList
    -0.07
    .IndexOf
    -0.07
    ayın
    -0.07
    .Symbol
    -0.07
     chores
    -0.06
     damning
    -0.06
     ز
    -0.06
     affordability
    -0.06
    .Restrict
    -0.06
    Ok
    -0.06
    POSITIVE LOGITS
    ulse
    0.07
     solitude
    0.06
     biz
    0.06
     wanted
    0.06
     innovative
    0.06
    annon
    0.06
    删除
    0.06
    _hat
    0.06
     Minh
    0.06
    eld
    0.06
    Act Density 0.000%

    No Known Activations