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

    Neuronpedia

    INDEX
    Explanations

    this

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    obel
    -0.07
    CELER
    -0.07
    X
    -0.07
     됩니다
    -0.06
    /O
    -0.06
    RF
    -0.06
     dispozici
    -0.06
     delay
    -0.06
    xx
    -0.06
    Brightness
    -0.06
    POSITIVE LOGITS
    platz
    0.07
     recruit
    0.07
     실
    0.06
     LOS
    0.06
    �
    0.06
     Dollars
    0.06
    DAL
    0.06
     Transportation
    0.06
     кім
    0.06
     Nun
    0.06
    Act Density 0.044%

    No Known Activations