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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _dump
    -0.07
     LINE
    -0.07
     Curtain
    -0.07
     labeled
    -0.07
    Modern
    -0.07
     thought
    -0.07
     first
    -0.07
     Says
    -0.06
     family
    -0.06
    H
    -0.06
    POSITIVE LOGITS
    .xaxis
    0.06
     Greenville
    0.06
     срав
    0.06
     댓글
    0.06
     situace
    0.06
    IntPtr
    0.06
    .jsx
    0.06
    ्थल
    0.06
    ойчив
    0.06
     philanth
    0.05
    Act Density 0.015%

    No Known Activations