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

    Neuronpedia

    INDEX
    Explanations

    technical/informational contexts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lenker
    -0.61
     Pokies
    -0.60
    expandindo
    -0.58
    Referències
    -0.56
    ρ
    -0.55
     StyleSheet
    -0.54
    ronique
    -0.53
     Grooming
    -0.53
     Truy
    -0.53
    zerne
    -0.52
    POSITIVE LOGITS
    jsonwebtoken
    0.49
    ValueGeneration
    0.47
     Chwiliwch
    0.47
     mathematicians
    0.47
    chwitz
    0.44
    EMPT
    0.44
    purl
    0.43
    amię
    0.43
    frå
    0.42
     verdura
    0.42
    Act Density 0.012%

    No Known Activations