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

    Neuronpedia

    INDEX
    Explanations

    introducing someone (dialogue)

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sık
    -0.08
    顯
    -0.07
     upstream
    -0.07
    .yaml
    -0.07
    zilla
    -0.07
    -0.07
    -league
    -0.07
     Phạm
    -0.07
     phys
    -0.06
     legalize
    -0.06
    POSITIVE LOGITS
    _gb
    0.07
    쌨
    0.07
    "]
↵
    0.07
    "]);↵
    0.07
    _metric
    0.07
     timespec
    0.07
    ('''
    0.07
    Corner
    0.07
    }),
    0.07
    "]↵
    0.06
    Act Density 0.062%

    No Known Activations