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

    Neuronpedia

    INDEX
    Explanations

    research studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    è·ª
    -0.27
    ä¸Ģéĥ¨
    -0.25
    idenav
    -0.25
    Enumer
    -0.25
     '&#
    -0.24
    ÑĩÑĮ
    -0.24
    ipi
    -0.24
    AccessType
    -0.24
     Gale
    -0.23
    edin
    -0.23
    POSITIVE LOGITS
    认为
    0.39
    éĥ½è®¤ä¸º
    0.36
     believe
    0.34
     believes
    0.33
    åĽłæѤ
    0.32
    marvin
    0.31
     therefore
    0.30
     thinks
    0.29
     hopes
    0.27
     said
    0.27
    Act Density 0.001%

    No Known Activations