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

    Neuronpedia

    INDEX
    Explanations

    biographies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     find
    -0.07
     themselves
    -0.06
    _daily
    -0.06
    division
    -0.06
     unconventional
    -0.06
    _drawer
    -0.06
    '),'
    -0.06
    .Table
    -0.06
     localize
    -0.06
    Employee
    -0.06
    POSITIVE LOGITS
     Klo
    0.07
    _MAJOR
    0.07
    .prot
    0.07
    constraints
    0.06
    jour
    0.06
    iếng
    0.06
    初
    0.06
     TypeInfo
    0.06
    зв
    0.06
    ={`
    0.06
    Act Density 0.018%

    No Known Activations