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

    Neuronpedia

    INDEX
    Explanations

    Multiple languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .package
    -0.07
    Re
    -0.06
     آنان
    -0.06
    ynchronized
    -0.06
    _unknown
    -0.06
     fur
    -0.06
     rested
    -0.06
     IOC
    -0.06
    velop
    -0.06
    On
    -0.06
    POSITIVE LOGITS
     says
    0.09
     сказав
    0.08
     saying
    0.08
     say
    0.08
     said
    0.08
     sagte
    0.08
     dijo
    0.07
     české
    0.07
     řekl
    0.07
     сказала
    0.07
    Act Density 0.029%

    No Known Activations