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

    Neuronpedia

    INDEX
    Explanations

    data structures and programming concepts related to regions and codes

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

    Code snippets with hexadecimal values

    np_acts-logits-general · gemini-2.0-flash

    from, to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    </strong>
    -0.64
    ‐
    -0.55
    mişti
    -0.55
     “
    -0.55
    ...
    -0.54
    cer
    -0.51
    ....
    -0.51
     فہرست
    -0.51
    “
    -0.49
     Fly
    -0.49
    POSITIVE LOGITS
     myſelf
    1.13
     Efq
    1.13
    ſelves
    1.11
     itſelf
    1.10
    ſelf
    1.09
     purpoſe
    1.08
     pleaſure
    1.07
     ſtate
    1.06
     ſche
    1.05
     Majefty
    1.01
    Act Density 3.834%

    No Known Activations