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

    Neuronpedia

    INDEX
    Explanations

    the suffix "ins" or the word "thereon"

    oai_token-act-pair · gemini-2.0-flash

    ins

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Efq
    -1.32
     Monfieur
    -1.19
     Shakspeare
    -1.19
     Cæsar
    -1.18
     myſelf
    -1.17
     Majefty
    -1.14
     Theſe
    -1.13
     Houſe
    -1.13
     Anſ
    -1.09
     Reſ
    -1.08
    POSITIVE LOGITS
    ↵↵
    1.09
    <eos>
    0.84
     a
    0.82
     The
    0.79
     the
    0.78
      
    0.75
     $
    0.75
     (
    0.73
     I
    0.72
     ...
    0.72
    Act Density 1.816%

    No Known Activations