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

    Neuronpedia

    INDEX
    Explanations

    the and this

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     billig
    -0.27
    æĸ½
    -0.26
     },↵↵↵
    -0.25
    å¨ģ
    -0.25
     locally
    -0.24
    èĬ
    -0.24
    irable
    -0.24
     Utils
    -0.23
    å¸ĺ
    -0.23
    çĦ¼
    -0.23
    POSITIVE LOGITS
    osas
    0.28
    èĨĽ
    0.27
    çļĦåľ°åĽ¾
    0.26
    ercul
    0.26
    genden
    0.26
     ps
    0.25
    greg
    0.25
     Below
    0.25
    ungs
    0.24
    ÑĩаÑĤ
    0.24
    Act Density 0.004%

    No Known Activations