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

    Neuronpedia

    INDEX
    Explanations

    |

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fallout
    -0.08
    Golden
    -0.07
    ovable
    -0.07
     Yong
    -0.06
     Archie
    -0.06
    AO
    -0.06
     Vak
    -0.06
                               ↵
    -0.06
     Guantanamo
    -0.06
     onDestroy
    -0.06
    POSITIVE LOGITS
    яют
    0.07
    translator
    0.06
     från
    0.06
    scription
    0.06
    کس
    0.06
    149
    0.06
    should
    0.06
    -handle
    0.06
    tree
    0.06
    .ibatis
    0.06
    Act Density 0.001%

    No Known Activations