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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Submitted
    -0.07
     STATIC
    -0.07
     všem
    -0.07
     Chess
    -0.06
     Pett
    -0.06
    <IM
    -0.06
     -----------
    -0.06
     Cooper
    -0.06
    �
    -0.06
     mesmer
    -0.06
    POSITIVE LOGITS
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.07
    nage
    0.07
    اسة
    0.06
    Expose
    0.06
    levard
    0.06
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.06
     eyed
    0.06
     annoyance
    0.06
    คล
    0.06
    cion
    0.06
    Act Density 0.013%

    No Known Activations