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

    Neuronpedia

    INDEX
    Explanations

    neg

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    asdf
    -0.07
    药师
    -0.07
    =input
    -0.07
    -vis
    -0.07
    atetime
    -0.07
    -offs
    -0.07
     tourist
    -0.07
    Attachment
    -0.07
     Volvo
    -0.07
     Explore
    -0.07
    POSITIVE LOGITS
    𝘯
    0.07
     phiên
    0.07
    _flag
    0.07
     fais
    0.06
    .reflect
    0.06
    Placeholder
    0.06
    �
    0.06
    套
    0.06
     revelations
    0.06
     initialized
    0.06
    Act Density 0.011%

    No Known Activations