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

    Neuronpedia

    INDEX
    Explanations

    strain

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uvo
    -0.07
     dinner
    -0.06
     Dinner
    -0.06
    fact
    -0.06
    люб
    -0.06
     Vehicle
    -0.06
     racing
    -0.06
    اق
    -0.06
    Faces
    -0.06
    Acc
    -0.06
    POSITIVE LOGITS
     strain
    0.19
     strains
    0.16
    strain
    0.07
    -effects
    0.07
    .StartsWith
    0.07
    ains
    0.07
    -dis
    0.07
    ConfigurationException
    0.07
     Antworten
    0.07
    ・・・
    0.07
    Act Density 0.004%

    No Known Activations