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

    Neuronpedia

    INDEX
    Explanations

    Data acquisition methods

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.08
    juan
    -0.07
    POCH
    -0.07
     BUT
    -0.07
    心头
    -0.07
    alli
    -0.07
    atio
    -0.07
    ༄
    -0.07
     Huntington
    -0.07
    ugo
    -0.07
    POSITIVE LOGITS
    ).↵↵↵
    0.09
     Decom
    0.08
     leftovers
    0.07
    展开
    0.07
    껌
    0.07
     paylaş
    0.07
     escorts
    0.07
    ---↵
    0.07
    =[],
    0.07
     Responsive
    0.07
    Act Density 0.000%

    No Known Activations