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

    Neuronpedia

    INDEX
    Explanations

    soft

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     отли
    -0.08
    воб
    -0.07
    .finish
    -0.07
    діл
    -0.06
     jdbc
    -0.06
    cluster
    -0.06
    	dir
    -0.06
     MF
    -0.06
     DEM
    -0.06
    _enter
    -0.06
    POSITIVE LOGITS
    turn
    0.08
    ếu
    0.07
    .microsoft
    0.07
     softly
    0.07
    払
    0.06
     brushing
    0.06
     origins
    0.06
    합
    0.06
     cannon
    0.06
    ationally
    0.06
    Act Density 0.015%

    No Known Activations