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

    Neuronpedia

    INDEX
    Explanations

    task

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     بیم
    -0.07
     fetal
    -0.07
     immigrant
    -0.07
    (len
    -0.06
     gallons
    -0.06
    TypeId
    -0.06
     magical
    -0.06
     sublime
    -0.06
    esh
    -0.06
    GPS
    -0.06
    POSITIVE LOGITS
     dec
    0.07
     cass
    0.06
    NSUInteger
    0.06
     sanctions
    0.06
    urther
    0.06
    UNCH
    0.06
    	util
    0.06
    TRY
    0.06
    	stage
    0.06
     周
    0.06
    Act Density 0.011%

    No Known Activations