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

    Neuronpedia

    INDEX
    Explanations

    Prime

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ifying
    -0.07
    accepted
    -0.07
    rowth
    -0.07
    арх
    -0.07
     repay
    -0.07
     dosud
    -0.06
    /#
    -0.06
    enk
    -0.06
    ъем
    -0.06
    .jms
    -0.06
    POSITIVE LOGITS
     sparse
    0.07
     Frequ
    0.07
     deque
    0.07
    Discuss
    0.06
     Palest
    0.06
     rotates
    0.06
    Resolver
    0.06
    .th
    0.06
    Goal
    0.06
     floats
    0.06
    Act Density 0.001%

    No Known Activations