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

    Neuronpedia

    INDEX
    Explanations

    People

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    root
    -0.28
    åįķåħĥ
    -0.27
    声åĵį
    -0.26
     darkness
    -0.25
     Jarvis
    -0.25
     Behind
    -0.24
    æĥ¹
    -0.23
    zer
    -0.23
     Pert
    -0.23
    light
    -0.23
    POSITIVE LOGITS
     advisers
    0.28
    åĪ¶çº¦
    0.26
     remarks
    0.26
    ascimento
    0.26
    ROKE
    0.26
    hower
    0.25
    ç½¢
    0.25
    étr
    0.25
    åįļè§Ī
    0.25
    å¬ĸ
    0.25
    Act Density 0.012%

    No Known Activations