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

    Neuronpedia

    INDEX
    Explanations

    Parsing language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ��
    -0.07
     ra
    -0.07
     دش
    -0.07
     وك
    -0.07
     �
    -0.06
    цес
    -0.06
     engulf
    -0.06
     bees
    -0.06
    ymi
    -0.06
     sugar
    -0.06
    POSITIVE LOGITS
     searching
    0.06
     busca
    0.06
     відом
    0.06
     Everett
    0.06
    gr
    0.06
     honoring
    0.06
    nullptr
    0.06
     Coff
    0.06
    ální
    0.06
    plně
    0.06
    Act Density 0.003%

    No Known Activations