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

    Neuronpedia

    INDEX
    Explanations

    announcing or introducing things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ยายาม
    0.95
     tentatives
    0.93
    trying
    0.87
     कोशिश
    0.85
     Basically
    0.84
    Basically
    0.83
     mainly
    0.83
     mostly
    0.83
     tries
    0.82
     basicamente
    0.81
    POSITIVE LOGITS
     announces
    1.52
     announced
    1.52
     announce
    1.51
     announcing
    1.50
     unveiled
    1.49
     unveils
    1.36
     today
    1.33
     introduces
    1.32
    announced
    1.32
     Introducing
    1.32
    Act Density 0.113%

    No Known Activations