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

    Neuronpedia

    INDEX
    Explanations

    hole

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cornwall
    -0.07
     Crab
    -0.06
    undos
    -0.06
    CPU
    -0.06
    fs
    -0.06
    兴
    -0.06
    صل
    -0.06
    过去
    -0.06
    violent
    -0.06
     Pax
    -0.06
    POSITIVE LOGITS
     productions
    0.07
     терап
    0.07
     acceptance
    0.07
    0.07
    .toByteArray
    0.06
    *=
    0.06
     Pharmaceutical
    0.06
     production
    0.06
    ●
    0.06
    Ac
    0.06
    Act Density 0.012%

    No Known Activations