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

    Neuronpedia

    INDEX
    Explanations

    unim

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    空中
    0.60
    地
    0.56
     தெரி
    0.51
     land
    0.50
    land
    0.49
     flesh
    0.49
     tort
    0.49
    শিক
    0.49
     eyes
    0.48
     release
    0.47
    POSITIVE LOGITS
     deputado
    0.74
     ergodic
    0.72
     juba
    0.70
     adenos
    0.70
    ुप
    0.69
    گرم
    0.69
    следова
    0.69
     große
    0.68
     serializers
    0.68
    ographers
    0.67
    Act Density 0.000%

    No Known Activations