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

    Neuronpedia

    INDEX
    Explanations

    body

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Package
    -0.07
     conference
    -0.07
     Conference
    -0.07
     athletes
    -0.06
    Ч
    -0.06
    ści
    -0.06
     permutations
    -0.06
    Rectangle
    -0.06
     musicians
    -0.06
     objectives
    -0.06
    POSITIVE LOGITS
    spd
    0.07
     RID
    0.07
    eh
    0.07
    .BAD
    0.06
     Fior
    0.06
     rotterdam
    0.06
    бом
    0.06
     multit
    0.06
     있음
    0.06
     ect
    0.05
    Act Density 0.041%

    No Known Activations