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

    Neuronpedia

    INDEX
    Explanations

    be

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ball
    -0.07
     of
    -0.07
     uuid
    -0.07
     Rectangle
    -0.07
    l
    -0.07
     выступ
    -0.07
     válido
    -0.06
    HEAD
    -0.06
     lush
    -0.06
     zoals
    -0.06
    POSITIVE LOGITS
     Freed
    0.06
    �试
    0.06
     Maps
    0.06
    aleur
    0.06
    仙
    0.06
     highs
    0.06
    .Amount
    0.05
     山
    0.05
     immortal
    0.05
     Monk
    0.05
    Act Density 0.030%

    No Known Activations