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

    Neuronpedia

    INDEX
    Explanations

    html anchor links

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    锦
    -0.07
     Chin
    -0.07
     Hyde
    -0.07
     trying
    -0.07
     Barton
    -0.06
     presented
    -0.06
    𝕷
    -0.06
    �
    -0.06
    ayers
    -0.06
     Lessons
    -0.06
    POSITIVE LOGITS
    .VALUE
    0.08
    �
    0.08
    weets
    0.07
    煤气
    0.07
    @admin
    0.07
    Subsystem
    0.07
    ANNEL
    0.07
    .notes
    0.07
    ⇤
    0.07
    =zeros
    0.06
    Act Density 0.031%

    No Known Activations