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

    Neuronpedia

    INDEX
    Explanations

    code endings like `});`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    譲
    0.72
     ride
    0.71
    启发
    0.70
    ácio
    0.68
    kind
    0.68
    letion
    0.68
     blessings
    0.67
    让
    0.67
     kicking
    0.67
     lett
    0.66
    POSITIVE LOGITS
    šnje
    0.77
    נים
    0.73
     	i
    0.73
    }\|^{
    0.72
     sigui
    0.70
     adulto
    0.70
     визнача
    0.70
    }');
    0.70
    ადგენ
    0.70
     annen
    0.69
    Act Density 0.001%

    No Known Activations