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

    Neuronpedia

    INDEX
    Explanations

    the word 'and' followed by an action word or verb

    oai_token-act-pair · gemini-2.0-flash

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -1.07
    లాలు
    -0.70
    ArgumentParser
    -0.66
    SharedCtor
    -0.63
     חיצוניים
    -0.63
    tagHelperRunner
    -0.63
    تفصیلات
    -0.62
    قایناقلار
    -0.62
     ProtoMessage
    -0.61
    lijks
    -0.56
    POSITIVE LOGITS
    IBOutlet
    0.57
    ніципалі
    0.53
    expandindo
    0.49
     onClose
    0.48
    izzling
    0.48
    fjspx
    0.47
    brücke
    0.47
    igurumi
    0.47
    WebControls
    0.47
     setInterval
    0.46
    Act Density 6.929%

    No Known Activations