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

    Neuronpedia

    INDEX
    Explanations

    say "version"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     accompagn
    -0.06
     navigate
    -0.06
    �
    -0.06
    Ms
    -0.06
     Kok
    -0.06
    蔓延
    -0.06
    ණ
    -0.06
     eux
    -0.06
     balk
    -0.06
     AJ
    -0.06
    POSITIVE LOGITS
    演习
    0.07
    .alert
    0.07
     chop
    0.06
    iological
    0.06
    手段
    0.06
    (database
    0.06
    nicas
    0.06
           
    0.06
     Punch
    0.06
     Procedure
    0.06
    Act Density 0.004%

    No Known Activations