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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences that convey information or directives

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

    tells us that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    endpush
    -0.64
    -0.56
     discussing
    -0.55
    Discussion
    -0.54
     discussion
    -0.54
    Discus
    -0.53
    discussion
    -0.52
    Sucesor
    -0.52
     Discussion
    -0.52
     discussions
    -0.51
    POSITIVE LOGITS
    mær
    0.46
     Vikipedi
    0.37
     sep
    0.35
    těte
    0.35
     σή
    0.34
     tells
    0.34
    abcdefghijklmnop
    0.33
    albero
    0.32
    meldung
    0.31
     savoir
    0.31
    Act Density 0.051%

    No Known Activations