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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ’in
    -0.06
    .isAdmin
    -0.06
    }while
    -0.06
    wing
    -0.06
    (':')[
    -0.06
    agues
    -0.06
    Processes
    -0.06
     el
    -0.06
     jednodu
    -0.06
    chair
    -0.06
    POSITIVE LOGITS
     معلومات
    0.07
    _right
    0.07
     svensk
    0.07
     Such
    0.06
     txn
    0.06
     없이
    0.06
     Madness
    0.06
    眼睛
    0.06
    Cro
    0.06
     Euros
    0.06
    Act Density 0.000%

    No Known Activations