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

    Neuronpedia

    INDEX
    Explanations

    ellipsis

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    🧹
    -0.10
     Belfast
    -0.08
    万名
    -0.08
    GetX
    -0.07
     NEG
    -0.07
    toHaveBeenCalledTimes
    -0.07
     freed
    -0.07
    .ToolStripButton
    -0.07
    帮扶
    -0.07
    膝盖
    -0.07
    POSITIVE LOGITS
    ……………………
    0.08
    …
    0.07
    aval
    0.07
     testament
    0.07
    castle
    0.07
    …↵↵
    0.07
    andering
    0.07
     Barton
    0.06
    fell
    0.06
    دل
    0.06
    Act Density 0.024%

    No Known Activations