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

    Neuronpedia

    INDEX
    Explanations

    We

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    binding
    -0.07
     TV
    -0.07
    DOMAIN
    -0.07
     treat
    -0.07
     FD
    -0.06
    aro
    -0.06
     unre
    -0.06
    рован
    -0.06
     television
    -0.06
    Inform
    -0.06
    POSITIVE LOGITS
    lüğü
    0.08
    0.07
    rewrite
    0.06
    ũng
    0.06
     scraps
    0.06
     consect
    0.06
    MJ
    0.06
     Evo
    0.06
     itr
    0.06
    ƒ
    0.06
    Act Density 0.036%

    No Known Activations