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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing conditional statements or requirements

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

    means that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ब्रेकडाउन
    -0.42
    いかが
    -0.40
     initWithFrame
    -0.37
    "):
    -0.36
    '));
    -0.36
    "},
    -0.35
    wantErr
    -0.35
    Véxase
    -0.35
    liseum
    -0.35
     Regret
    -0.35
    POSITIVE LOGITS
    ardoor
    0.63
    这意味着
    0.56
     Consequently
    0.53
     disambiguazione
    0.52
    Consequently
    0.52
     consequently
    0.50
     nonUne
    0.50
     means
    0.50
    sprechend
    0.49
     betyr
    0.48
    Act Density 0.022%

    No Known Activations