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

    Neuronpedia

    INDEX
    Explanations

    between

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reflex
    -0.08
    Brief
    -0.06
     veh
    -0.06
     wel
    -0.06
     mediante
    -0.06
     figur
    -0.06
     gele
    -0.06
     childs
    -0.06
    micro
    -0.06
     recomend
    -0.06
    POSITIVE LOGITS
    993
    0.06
    اند
    0.06
    ↑
    0.06
     GAM
    0.06
    _hash
    0.06
    _contact
    0.06
    لام
    0.06
    †
    0.06
     ward
    0.06
    ��
    0.06
    Act Density 0.017%

    No Known Activations