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

    Neuronpedia

    INDEX
    Explanations

    variable assignment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     =
    1.07
     ="
    0.88
     =[
    0.82
     ='
    0.75
    =[
    0.74
    =['
    0.73
     $=\
    0.71
    =[]
    0.70
     <-
    0.69
     $=
    0.67
    POSITIVE LOGITS
     tepat
    0.72
     televiz
    0.69
     వివా
    0.69
    umsal
    0.69
     televisie
    0.67
    !!!");
    0.67
    exactly
    0.66
     tegas
    0.66
     magní
    0.66
    Acetoxy
    0.66
    Act Density 0.043%

    No Known Activations