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

    Neuronpedia

    INDEX
    Explanations

    names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    emplates
    -0.31
     Desmond
    -0.28
    éľ°
    -0.27
    EDIUM
    -0.26
    ilty
    -0.26
    åĪĨæķ£
    -0.25
    usted
    -0.25
    æ·¬
    -0.25
    emplate
    -0.24
    orsch
    -0.24
    POSITIVE LOGITS
     кино
    0.27
    ಹ
    0.27
    æĬ¤èĤ¤
    0.27
     Aware
    0.26
    Pocket
    0.26
     cinéma
    0.25
    Gear
    0.25
    æ´¾
    0.24
     Kids
    0.24
     kids
    0.24
    Act Density 0.020%

    No Known Activations