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

    Neuronpedia

    INDEX
    Explanations

    expressions indicating major problems or challenges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    BIO type

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ut
    -0.43
     
    -0.40
     tot
    -0.40
    lo
    -0.37
    read
    -0.37
     infine
    -0.36
     plus
    -0.35
     his
    -0.35
     Bar
    -0.35
    lop
    -0.35
    POSITIVE LOGITS
     Monfieur
    1.03
     Theſe
    1.02
     Efq
    1.02
     becauſe
    0.99
     Jefus
    0.98
     Majefty
    0.98
    \{\\
    0.97
     виправивши
    0.94
     purpoſe
    0.94
     ſtate
    0.93
    Act Density 0.162%

    No Known Activations