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

    Neuronpedia

    INDEX
    Explanations

    physics operators

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ")!=
    -0.07
    ")==
    -0.07
    .compute
    -0.06
    talk
    -0.06
    !=
    -0.06
     queue
    -0.06
    Editing
    -0.06
    平台
    -0.06
    _scale
    -0.06
    energy
    -0.06
    POSITIVE LOGITS
    IFT
    0.06
     gruesome
    0.06
     videoer
    0.06
    /$',
    0.06
     charakter
    0.06
     debuted
    0.06
    イク
    0.06
    ablish
    0.06
     ago
    0.06
     де
    0.06
    Act Density 0.007%

    No Known Activations