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

    Neuronpedia

    INDEX
    Explanations

    references to specific neural network architectures and their variants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    LF-Net and ELF-LFNet

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     zoom
    -0.55
    IORITY
    -0.52
    存于互联网档案馆
    -0.51
     Zoom
    -0.50
     Buchanan
    -0.50
    ="@
    -0.50
    pytest
    -0.50
     ZOOM
    -0.50
     jButton
    -0.49
     Weaver
    -0.49
    POSITIVE LOGITS
    LF
    2.16
    lf
    2.03
     LF
    1.98
     lf
    1.65
    Lf
    1.30
    lfs
    0.94
    elf
    0.85
    ELF
    0.79
     ELF
    0.77
    ULF
    0.76
    Act Density 0.015%

    No Known Activations