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

    Neuronpedia

    INDEX
    Explanations

    Saying or repeating something

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ētu
    -0.10
    .firebase
    -0.08
     वर्ण
    -0.08
     उत्प
    -0.08
    _globals
    -0.08
    _blk
    -0.08
     lst
    -0.08
    /firebase
    -0.08
    .lst
    -0.08
     उत्स
    -0.08
    POSITIVE LOGITS
     aclar
    0.10
    Reminder
    0.10
     Reminder
    0.10
     tyd
    0.10
     claramente
    0.10
    Underline
    0.10
     clairement
    0.10
     reminder
    0.09
     reiterated
    0.09
     clara
    0.09
    Act Density 0.108%

    No Known Activations