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

    Neuronpedia

    INDEX
    Explanations

    data structure elements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     মত
    -0.08
     Yank
    -0.08
     Meinung
    -0.08
     verdad
    -0.08
     netto
    -0.07
     буенча
    -0.07
     ол
    -0.07
    แกรม
    -0.07
     Find
    -0.07
    ndr
    -0.07
    POSITIVE LOGITS
    તમાં
    0.08
    િત
    0.08
     തന്നെ
    0.07
     sodass
    0.07
    Touched
    0.07
    [...]
    0.07
     enthalten
    0.07
    .include
    0.07
     embed
    0.07
    시에
    0.07
    Act Density 0.047%

    No Known Activations