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

    Neuronpedia

    INDEX
    Explanations

    specialized phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bias
    0.39
    ន្
    0.38
    ੱ
    0.38
     अनुपात
    0.38
     intimidating
    0.38
    槌
    0.37
     gewinnen
    0.37
    誼
    0.37
     rapp
    0.36
     iso
    0.36
    POSITIVE LOGITS
    (\
    0.42
    ছার
    0.42
    是为了
    0.40
    ());
    0.40
    Child
    0.39
    aggregation
    0.39
    (((
    0.38
    alım
    0.38
    Aggregation
    0.38
    meteor
    0.38
    Act Density 0.000%

    No Known Activations