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

    Neuronpedia

    INDEX
    Explanations

    from is to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     repeatedly
    -0.08
     aura
    -0.06
     tor
    -0.06
     steadily
    -0.06
    	ll
    -0.06
     yoksa
    -0.06
     cone
    -0.06
     nihil
    -0.06
    .Ref
    -0.06
    公開
    -0.06
    POSITIVE LOGITS
     conceal
    0.07
     IQueryable
    0.07
     pled
    0.07
     STREET
    0.06
    egis
    0.06
    Drive
    0.06
    /;↵
    0.06
     gchar
    0.06
    '];
↵
    0.06
    キング
    0.06
    Act Density 0.002%

    No Known Activations