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

    Neuronpedia

    INDEX
    Explanations

    methods and techniques

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _network
    -0.07
    duce
    -0.07
    wan
    -0.06
    rends
    -0.06
    .music
    -0.06
     tn
    -0.06
    Experiment
    -0.06
    الي
    -0.06
    'url
    -0.06
     tiêu
    -0.06
    POSITIVE LOGITS
     Bron
    0.06
     Tactics
    0.06
     Dış
    0.06
    営
    0.06
    改
    0.06
     fondo
    0.06
     어머니
    0.06
     Nord
    0.06
    ใช
    0.06
    aut
    0.06
    Act Density 0.199%

    No Known Activations