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

    Neuronpedia

    INDEX
    Explanations

    Diversity and inclusion

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    绾
    -0.08
    	Py
    -0.08
    傲
    -0.08
     swal
    -0.07
    @endforeach
    -0.07
    *)((
    -0.07
    AUDIO
    -0.07
    .awt
    -0.07
    �
    -0.07
    ◬
    -0.07
    POSITIVE LOGITS
     MODE
    0.07
    密码
    0.07
    	b
    0.07
     account
    0.07
     brig
    0.07
    .Op
    0.06
     Weather
    0.06
    -error
    0.06
     Boundary
    0.06
     WR
    0.06
    Act Density 0.027%

    No Known Activations