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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .depart
    -0.07
     share
    -0.07
     physics
    -0.07
     prayer
    -0.06
     Iowa
    -0.06
     remembers
    -0.06
    ALER
    -0.06
     трав
    -0.06
     kâ
    -0.06
     piger
    -0.06
    POSITIVE LOGITS
     Habitat
    0.07
    總
    0.07
    �다
    0.07
    uridad
    0.06
     السكان
    0.06
    adır
    0.06
    ilendir
    0.06
    łe
    0.06
     Benghazi
    0.06
    ')));↵
    0.06
    Act Density 0.035%

    No Known Activations