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

    Neuronpedia

    INDEX
    Explanations

    include

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     goalie
    -0.07
    periment
    -0.07
    orum
    -0.07
    -chief
    -0.07
     Galaxy
    -0.07
    Queue
    -0.07
     outrageous
    -0.07
     quieter
    -0.07
    quip
    -0.06
    -rock
    -0.06
    POSITIVE LOGITS
    _android
    0.06
    ><?=$
    0.06
    =target
    0.06
    tiny
    0.06
    บบ
    0.06
    шт
    0.06
    撮
    0.06
     bless
    0.06
     ISBN
    0.06
    ,module
    0.06
    Act Density 0.012%

    No Known Activations