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

    Neuronpedia

    INDEX
    Explanations

    ellipses or omissions in text

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

    closing parenthesis or brace

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    guint
    -0.43
     Pend
    -0.41
     שע
    -0.38
    Euc
    -0.37
    <bos>
    -0.36
    loem
    -0.36
     Pav
    -0.36
    pulumi
    -0.35
    dsp
    -0.35
     tenet
    -0.35
    POSITIVE LOGITS
     ...
    1.35
     ..."
    1.10
     ...)
    1.10
     ...]
    1.01
     ....
    1.01
     ...
    1.00
     ...,
    0.98
     ...'
    0.96
     …
    0.92
     .....
    0.90
    Act Density 0.014%

    No Known Activations