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

    Neuronpedia

    INDEX
    Explanations

    information

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    essment
    -0.07
    Macro
    -0.06
     gender
    -0.06
    cih
    -0.06
    .light
    -0.06
    _ROLE
    -0.06
     tương
    -0.05
    ôi
    -0.05
    �
    -0.05
     metast
    -0.05
    POSITIVE LOGITS
     information
    0.08
     Information
    0.07
    출장샵
    0.07
    ーブ
    0.06
    Profiler
    0.06
    .RemoveAt
    0.06
    -st
    0.06
     σχέ
    0.06
    INFO
    0.06
    .pnl
    0.06
    Act Density 0.009%

    No Known Activations