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

    Neuronpedia

    INDEX
    Explanations

    file paths and directories

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     index
    -0.07
     Xi
    -0.07
     divisible
    -0.07
     denounced
    -0.07
    惆
    -0.06
    xor
    -0.06
    鲜明
    -0.06
    低
    -0.06
     markedly
    -0.06
    なんか
    -0.06
    POSITIVE LOGITS
    俫
    0.08
    sión
    0.08
     теб
    0.07
    حضار
    0.07
    洳
    0.07
     incarcer
    0.07
     warmed
    0.07
    鲺
    0.07
    .station
    0.07
     EditorGUILayout
    0.07
    Act Density 0.087%

    No Known Activations