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

    Neuronpedia

    INDEX
    Explanations

    countries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ятий
    -0.07
    erty
    -0.07
     mockery
    -0.07
     Fet
    -0.06
     Pandora
    -0.06
    ancock
    -0.06
     hiring
    -0.06
    _PW
    -0.06
    ünde
    -0.06
     タ
    -0.06
    POSITIVE LOGITS
    roj
    0.07
    OnClickListener
    0.07
     stout
    0.06
     Completion
    0.06
    งก
    0.06
     XK
    0.06
     Taipei
    0.06
     turist
    0.06
     Ich
    0.06
    ไม
    0.06
    Act Density 0.001%

    No Known Activations