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

    Neuronpedia

    INDEX
    Explanations

    favorite

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     verh
    -0.09
     Permanent
    -0.08
     пространства
    -0.08
    Permanent
    -0.08
     demi
    -0.08
    ahs
    -0.08
     furnished
    -0.08
    يح
    -0.07
    alem
    -0.07
     Cin
    -0.07
    POSITIVE LOGITS
    avorite
    0.09
     hashtags
    0.08
     만큼
    0.08
    favorite
    0.08
     Obl
    0.08
     favorite
    0.08
     favoritas
    0.07
     trae
    0.07
     ప్రముఖ
    0.07
    estors
    0.07
    Act Density 0.026%

    No Known Activations