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

    Neuronpedia

    INDEX
    Explanations

    asides and commentary

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Payload
    -0.08
     traje
    -0.07
    /job
    -0.07
    pled
    -0.07
     �
    -0.07
     nust
    -0.07
    /apple
    -0.07
     whitelist
    -0.07
     CSI
    -0.07
     lĩnh
    -0.07
    POSITIVE LOGITS
     occasional
    0.12
    Throughout
    0.12
     মাঝে
    0.11
     Throughout
    0.10
     Occasionally
    0.10
     occasionally
    0.10
     במהלך
    0.10
     throughout
    0.10
     ocas
    0.09
    Комментарии
    0.09
    Act Density 0.053%

    No Known Activations