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

    Neuronpedia

    INDEX
    Explanations

    start of user instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    praw
    0.38
    IME
    0.38
     down
    0.36
    ime
    0.36
     denote
    0.36
     arranges
    0.35
     largely
    0.34
     guts
    0.34
    Zur
    0.34
     ordered
    0.34
    POSITIVE LOGITS
    </h3>
    0.84
    subsubsection
    0.47
    <h3>
    0.46
    </img>
    0.41
    '/>
    0.41
     \\
    0.40
    ▾
    0.40
    </h6>
    0.39
    ###
    0.39
    सम
    0.39
    Act Density 0.003%

    No Known Activations