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

    Neuronpedia

    INDEX
    Explanations

    instances of negation and phrases concerning the absence of something

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

    Following "without" or variants

    np_acts-logits-general · gemini-2.0-flash

    without any

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    enumii
    -0.71
     صوتيه
    -0.68
    <unused68>
    -0.66
    <unused3>
    -0.66
    bildtitel
    -0.66
    <unused47>
    -0.66
    Personensuche
    -0.66
    <unused79>
    -0.66
    <unused41>
    -0.66
    <unused42>
    -0.66
    POSITIVE LOGITS
     without
    0.60
     tanpa
    0.50
     Without
    0.47
    Without
    0.43
    without
    0.42
     senza
    0.40
     ohne
    0.38
     Senza
    0.38
    Ohne
    0.38
     بدون
    0.36
    Act Density 0.411%

    No Known Activations