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

    Neuronpedia

    INDEX
    Explanations

    Code snippets and technical language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    constitutional
    -0.07
     التونسي
    -0.07
     accommodating
    -0.07
     though
    -0.07
     Tooth
    -0.07
     Conditioning
    -0.07
    foundland
    -0.07
    imoto
    -0.07
     Holmes
    -0.07
     Unfortunately
    -0.07
    POSITIVE LOGITS
     rave
    0.07
     Palo
    0.07
    �
    0.07
    禾
    0.07
     repertoire
    0.07
    Rol
    0.07
    二级
    0.07
     каждого
    0.07
    _Index
    0.06
     mơ
    0.06
    Act Density 0.064%

    No Known Activations