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

    Neuronpedia

    INDEX
    Explanations

    safe

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Sections
    -0.07
    lád
    -0.07
     allocator
    -0.07
     dür
    -0.06
     Manuals
    -0.06
     ['-
    -0.06
    ым
    -0.06
     proposals
    -0.06
     άλ
    -0.06
    くら
    -0.06
    POSITIVE LOGITS
     ssid
    0.07
    responseData
    0.07
    EZ
    0.06
     taught
    0.06
    explicit
    0.06
     pirate
    0.06
    _TICK
    0.06
    .DefaultCellStyle
    0.06
     depicting
    0.06
    491
    0.06
    Act Density 0.004%

    No Known Activations