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

    Neuronpedia

    INDEX
    Explanations

    4

    np_max-act · gemini-2.0-flash

    queries related to comparisons of size or magnitude.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    gressor
    -0.08
     contaminated
    -0.07
     crossings
    -0.07
    706
    -0.07
     다양
    -0.07
    social
    -0.06
    odia
    -0.06
    oxid
    -0.06
     washing
    -0.06
     noises
    -0.06
    POSITIVE LOGITS
     trắng
    0.07
     köş
    0.07
     основе
    0.07
    (EX
    0.06
    auty
    0.06
     تیم
    0.06
    ?>:</
    0.06
    embre
    0.06
     тру
    0.06
    (inv
    0.06
    Act Density 0.153%

    No Known Activations