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

    Neuronpedia

    INDEX
    Explanations

    adults

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mnoho
    -0.07
    説明
    -0.07
    Ja
    -0.07
     TEAM
    -0.06
     Dün
    -0.06
    relationships
    -0.06
    specialchars
    -0.06
    анти
    -0.06
     är
    -0.06
    yi
    -0.06
    POSITIVE LOGITS
     percentage
    0.07
     classifications
    0.06
     decorator
    0.06
    irection
    0.06
    ∨
    0.06
    HB
    0.06
     regardless
    0.06
     illustration
    0.06
     radiation
    0.06
    ,dim
    0.06
    Act Density 0.176%

    No Known Activations