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

    Neuronpedia

    INDEX
    Explanations

    mathematical/numerical problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     triun
    -0.07
    兴
    -0.07
     Me
    -0.07
    wish
    -0.07
    ################################
    -0.07
    Me
    -0.06
     herbal
    -0.06
     Objet
    -0.06
     सर्व
    -0.06
     workable
    -0.06
    POSITIVE LOGITS
     restantes
    0.09
    нес
    0.09
    -за
    0.09
     nào
    0.09
     pertence
    0.08
     belonging
    0.08
     pagitan
    0.08
     helft
    0.08
     Reserved
    0.08
    番号
    0.08
    Act Density 0.091%

    No Known Activations