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

    Neuronpedia

    INDEX
    Explanations

    business/research/technology

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Init
    -0.08
    では
    -0.08
    κας
    -0.07
     footsteps
    -0.06
     Greek
    -0.06
    aky
    -0.06
     flying
    -0.06
     Neal
    -0.06
     vec
    -0.06
    InitStruct
    -0.06
    POSITIVE LOGITS
    readcr
    0.07
     ingestion
    0.07
     premiums
    0.06
     MÜ
    0.06
     heaters
    0.06
    gression
    0.06
     energies
    0.06
     LT
    0.06
     жен
    0.06
     gradients
    0.06
    Act Density 0.370%

    No Known Activations