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

    Neuronpedia

    INDEX
    Explanations

    code/keys

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    æľ
    -0.27
    itas
    -0.27
    lights
    -0.27
    åīįæīĢ
    -0.26
    åįĸæİī
    -0.26
     markers
    -0.26
    erval
    -0.25
     scores
    -0.25
    lard
    -0.24
     hone
    -0.24
    POSITIVE LOGITS
     duro
    0.28
     milit
    0.27
    sci
    0.26
    æ½ľèīĩ
    0.26
    çļĦå¿ĥçIJĨ
    0.26
     ÑĢаÑģÑģ
    0.26
    å±¥
    0.26
     submarines
    0.26
    _atoms
    0.25
    çĶ¬
    0.25
    Act Density 1.615%

    No Known Activations