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

    Neuronpedia

    INDEX
    Explanations

    former

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    II
    -0.07
    .Ac
    -0.06
     tho
    -0.06
    -final
    -0.06
    红
    -0.06
     FE
    -0.06
     不
    -0.06
     कम
    -0.06
    mach
    -0.06
     dan
    -0.06
    POSITIVE LOGITS
     hateful
    0.06
    (Table
    0.06
    .binary
    0.06
    _cor
    0.06
     Anyone
    0.06
    -double
    0.06
    ##↵↵
    0.06
    pecting
    0.06
    ompiler
    0.06
    *****↵↵
    0.06
    Act Density 0.040%

    No Known Activations