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

    Neuronpedia

    INDEX
    Explanations

    Limits or boundaries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     accusation
    -0.07
     subdivisions
    -0.07
     boosted
    -0.07
     найд
    -0.06
    ctxt
    -0.06
     launches
    -0.06
     biome
    -0.06
     nto
    -0.06
     mocked
    -0.06
     लड
    -0.06
    POSITIVE LOGITS
    .setOutput
    0.07
    .imgur
    0.07
    350
    0.07
     Firm
    0.07
    _AF
    0.07
     участи
    0.06
    avic
    0.06
    辰
    0.06
    αν
    0.06
    览
    0.06
    Act Density 0.262%

    No Known Activations