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

    Neuronpedia

    INDEX
    Explanations

    structured visual descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    desPort
    0.44
    grown
    0.40
    ર્ગ
    0.39
     breakfasts
    0.39
    dez
    0.38
    \%).
    0.38
    dried
    0.38
    iterations
    0.38
    \&
    0.37
    rü
    0.37
    POSITIVE LOGITS
     |
    0.46
    ██
    0.46
     │
    0.44
     Últ
    0.43
    |
    0.42
     "|
    0.40
     /
    0.39
     conf
    0.39
     四
    0.39
     (|
    0.38
    Act Density 0.011%

    No Known Activations