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

    Neuronpedia

    INDEX
    Explanations

    instructions and setting parameters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ç»ıéªĮ
    -0.32
    å½Ī
    -0.29
    å¼¹
    -0.28
     =========================================================================
    -0.28
    æīĭå¥Ĺ
    -0.28
     persec
    -0.27
    ITO
    -0.26
    Experience
    -0.25
    åĪ¶åº¦æĶ¹éĿ©
    -0.25
    Ṭ
    -0.25
    POSITIVE LOGITS
     incorrectly
    0.29
    est
    0.28
     indirectly
    0.27
    atLng
    0.25
    å³Ļ
    0.25
     delivered
    0.25
    GetString
    0.25
     boundary
    0.24
     neighbor
    0.24
     playground
    0.23
    Act Density 0.009%

    No Known Activations