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

    Neuronpedia

    INDEX
    Explanations

    identifiers and codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    িয়াছেন
    0.36
    uyorum
    0.32
    _',
    0.31
     abstinence
    0.30
    piej
    0.30
    kommt
    0.30
    Ꮺ
    0.30
    Zu
    0.29
     poop
    0.29
    σουμε
    0.29
    POSITIVE LOGITS
     Test
    0.35
     -
    0.31
     Interface
    0.30
     Project
    0.30
     No
    0.29
    ा
    0.29
     Even
    0.29
     Page
    0.29
     Photo
    0.29
    -
    0.29
    Act Density 0.001%

    No Known Activations