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

    Neuronpedia

    INDEX
    Explanations

    400

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    peace
    -0.07
     articulated
    -0.06
    007
    -0.06
     refute
    -0.06
    QN
    -0.06
    715
    -0.06
    �
    -0.06
    πό
    -0.06
     히
    -0.06
     routinely
    -0.06
    POSITIVE LOGITS
    NavigationView
    0.07
    (Log
    0.07
    parm
    0.07
    arry
    0.07
     Relation
    0.06
    (fid
    0.06
     Mur
    0.06
     Coat
    0.06
     تاب
    0.06
    (buf
    0.06
    Act Density 0.000%

    No Known Activations