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

    Neuronpedia

    INDEX
    Explanations

    state

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uss
    -0.08
     disagree
    -0.07
    ze
    -0.07
    licity
    -0.07
     convers
    -0.07
    بر
    -0.07
     wheel
    -0.07
    哲学
    -0.07
    .bar
    -0.07
     viol
    -0.07
    POSITIVE LOGITS
    日趋
    0.07
    烦躁
    0.07
    .family
    0.07
     worsh
    0.06
    ꦩ
    0.06
    CGRect
    0.06
    intégr
    0.06
     Kashmir
    0.06
    (func
    0.06
     Angus
    0.06
    Act Density 0.013%

    No Known Activations