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

    Neuronpedia

    INDEX
    Explanations

    medical incidence/rarity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Jackie
    -0.06
     Γκ
    -0.06
    上的
    -0.06
    	ERR
    -0.06
    되지
    -0.06
    Resolve
    -0.06
    ある
    -0.06
     Yosh
    -0.06
     الثاني
    -0.06
     storia
    -0.06
    POSITIVE LOGITS
     Residence
    0.07
     Flavor
    0.07
    weis
    0.06
     наст
    0.06
    inion
    0.06
    _ALLOWED
    0.06
    Disclosure
    0.06
    tement
    0.06
     multicultural
    0.06
    Lik
    0.06
    Act Density 0.038%

    No Known Activations