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

    Neuronpedia

    INDEX
    Explanations

    differentiate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     وش
    -0.06
     pursuing
    -0.06
     ambush
    -0.06
    Tem
    -0.06
     Maj
    -0.06
    魂
    -0.06
     PIL
    -0.06
     necessary
    -0.06
     блю
    -0.06
    095
    -0.06
    POSITIVE LOGITS
     differentiate
    0.14
     differentiated
    0.12
     differentiation
    0.10
    iffer
    0.08
    посеред
    0.07
     bulunur
    0.07
    .autoconfigure
    0.07
     Northeast
    0.07
    theast
    0.07
     자유
    0.07
    Act Density 0.006%

    No Known Activations