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

    Neuronpedia

    INDEX
    Explanations

    these

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     credibility
    -0.08
    arena
    -0.07
     problema
    -0.07
    Ada
    -0.07
     borderline
    -0.07
     strt
    -0.07
     crem
    -0.06
     toplam
    -0.06
     asign
    -0.06
    cgi
    -0.06
    POSITIVE LOGITS
    Binding
    0.06
    좌
    0.06
    "';
    0.06
     Creatures
    0.06
    key
    0.06
     waters
    0.06
    -not
    0.06
     intervening
    0.06
    _white
    0.06
     ('\
    0.06
    Act Density 0.275%

    No Known Activations