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

    Neuronpedia

    INDEX
    Explanations

    Language and character strings

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .ping
    -0.07
     гип
    -0.07
    .services
    -0.07
     Opport
    -0.06
    .real
    -0.06
     fid
    -0.06
    .MULT
    -0.06
     mistaken
    -0.06
    localctx
    -0.06
    Theta
    -0.06
    POSITIVE LOGITS
     Valid
    0.07
    (vertex
    0.06
    ząd
    0.06
     Tom
    0.06
    ynchronous
    0.06
    (training
    0.06
    (speed
    0.06
     joe
    0.06
     Coach
    0.06
     Orders
    0.06
    Act Density 0.065%

    No Known Activations