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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate potential actions or possibilities

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

    what is possible

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     assise
    -0.50
     specifiche
    -0.44
    层面
    -0.43
     aikaa
    -0.42
     duradero
    -0.40
     Masyarakat
    -0.40
     olisi
    -0.38
     Penggunaan
    -0.38
     redacción
    -0.38
     siihen
    -0.38
    POSITIVE LOGITS
    possible
    1.10
     Possible
    1.05
    Possible
    1.03
     possible
    1.01
    impossible
    1.00
     Impossible
    0.96
    Impossible
    0.96
    Possibility
    0.96
    POSSIBLE
    0.95
    possibility
    0.95
    Act Density 0.058%

    No Known Activations