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

    Neuronpedia

    INDEX
    Explanations

    articles/prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     shady
    -0.07
    ceries
    -0.06
     �
    -0.06
     ocor
    -0.06
    eyJ
    -0.06
    cone
    -0.06
    jadi
    -0.06
    .soft
    -0.06
     γνω
    -0.06
    _unsigned
    -0.06
    POSITIVE LOGITS
     первый
    0.06
    altung
    0.06
    ataset
    0.06
     Weapon
    0.06
    asha
    0.06
    a
    0.06
     slag
    0.06
     delivery
    0.06
     homage
    0.06
     existing
    0.06
    Act Density 0.022%

    No Known Activations