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

    Neuronpedia

    INDEX
    Explanations

    quotes followed by s or x

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ge
    0.77
    G
    0.74
    Mg
    0.74
    lge
    0.70
     Mg
    0.70
     Gw
    0.68
    weight
    0.67
    GL
    0.66
     mg
    0.66
    Ge
    0.66
    POSITIVE LOGITS
     Cervantes
    1.29
    spiral
    1.24
     Irr
    1.19
     dauer
    1.18
     Roper
    1.18
     Sauv
    1.18
     Andover
    1.17
     Saunders
    1.17
     Brenner
    1.16
     Turtle
    1.15
    Act Density 1.458%

    No Known Activations