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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     conduct
    -0.07
     curse
    -0.07
    Leo
    -0.07
    otp
    -0.06
    Agency
    -0.06
    Hands
    -0.06
     Ru
    -0.06
     Leo
    -0.06
    Sa
    -0.06
     URI
    -0.06
    POSITIVE LOGITS
     provád
    0.07
    (match
    0.06
    .TextImageRelation
    0.06
    .TryGetValue
    0.06
    .JsonProperty
    0.06
     美国
    0.06
    .compareTo
    0.06
     poco
    0.06
    (NULL
    0.06
     необходим
    0.06
    Act Density 0.000%

    No Known Activations