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

    Neuronpedia

    INDEX
    Explanations

    fixing CoffeeScript or text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Agg
    0.46
    c
    0.46
     Savage
    0.45
    нити
    0.45
    ll
    0.45
    ordable
    0.45
    regon
    0.45
    filenames
    0.45
    aran
    0.44
     расши
    0.44
    POSITIVE LOGITS
     wealthy
    0.55
    ه
    0.54
     influential
    0.49
     wpły
    0.47
    سطس
    0.46
     identified
    0.46
    ي
    0.46
     citizens
    0.46
     climbers
    0.45
     glavni
    0.45
    Act Density 0.000%

    No Known Activations