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

    Neuronpedia

    INDEX
    Explanations

    instances of something being impossible, blocked, or harmed.

    oai_token-act-pair · gemini-2.0-flash

    difficulty or impossibility

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     den
    -0.67
     Mi
    -0.65
     \
    -0.65
     utafitiHapana
    -0.65
     des
    -0.63
    ):=\
    -0.63
     tras
    -0.62
     au
    -0.61
     id
    -0.60
     Ma
    -0.59
    POSITIVE LOGITS
     Monfieur
    1.66
     myſelf
    1.59
     themſelves
    1.51
     Majefty
    1.50
     Jefus
    1.48
     itſelf
    1.46
     Theſe
    1.43
     Houſe
    1.39
     Efq
    1.38
     Diſ
    1.35
    Act Density 1.651%

    No Known Activations