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

    Neuronpedia

    INDEX
    Explanations

    appreciation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Signup
    -0.07
    iedo
    -0.07
    	dialog
    -0.06
    ائب
    -0.06
    olvable
    -0.06
    МО
    -0.06
    png
    -0.06
     VER
    -0.06
    rawing
    -0.06
    الق
    -0.06
    POSITIVE LOGITS
    این
    0.07
     express
    0.06
     Finland
    0.06
     adjusts
    0.06
     hairstyle
    0.06
    ौड
    0.06
     distinguishing
    0.06
     divisions
    0.06
     Ward
    0.06
     drive
    0.06
    Act Density 0.030%

    No Known Activations