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

    Neuronpedia

    INDEX
    Explanations

    Naming or referring

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    jid
    -0.27
    åĬŀ
    -0.26
    TÄ°
    -0.25
    åĮħ
    -0.24
     operating
    -0.24
    uries
    -0.24
    .opens
    -0.24
    resse
    -0.24
     hook
    -0.24
     spos
    -0.23
    POSITIVE LOGITS
     Kut
    0.26
     Everywhere
    0.25
    æĺ¨å¤©
    0.25
     secara
    0.25
    ombine
    0.24
    åĩĽ
    0.24
    .asList
    0.24
    åĺĺ
    0.24
    çµIJåIJĪ
    0.23
    Compat
    0.23
    Act Density 0.003%

    No Known Activations