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

    Neuronpedia

    INDEX
    Explanations

    Naming or designation within text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    لمة
    -0.07
    .k
    -0.07
     соот
    -0.07
    Male
    -0.07
    _sender
    -0.06
    학과
    -0.06
    แลนด
    -0.06
    asurer
    -0.06
    (test
    -0.06
     etmiştir
    -0.06
    POSITIVE LOGITS
    :UIControlState
    0.07
     prac
    0.06
    agy
    0.06
     unstable
    0.06
     ide
    0.06
     alerts
    0.06
     LEFT
    0.05
     Ny
    0.05
    _GT
    0.05
    :id
    0.05
    Act Density 0.014%

    No Known Activations