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

    Neuronpedia

    INDEX
    Explanations

    phrases related to health metrics and symptoms

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

    Contractions and informal spellings

    np_acts-logits-general · gemini-2.0-flash

    what if it was

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     –,
    -0.82
     yalnızca
    -0.81
     iſt
    -0.81
     uſ
    -0.78
     ―――――
    -0.77
     ſhould
    -0.77
     itſelf
    -0.75
     ſind
    -0.75
     ſi
    -0.74
     ſhall
    -0.74
    POSITIVE LOGITS
     alot
    1.06
     наверное
    0.86
     dont
    0.83
     didnt
    0.82
    慢慢的
    0.82
     doesnt
    0.81
     wasnt
    0.79
     thats
    0.78
     whats
    0.78
     ppl
    0.77
    Act Density 2.506%

    No Known Activations