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

    Neuronpedia

    INDEX
    Explanations

    supporting ON

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    oretically
    0.43
    迩
    0.40
    ierte
    0.39
    ixas
    0.36
    ille
    0.36
    ात
    0.36
    లు
    0.35
    ValueChanged
    0.34
     gro
    0.33
     Kreis
    0.33
    POSITIVE LOGITS
     thereof
    0.89
     tejto
    0.82
     acest
    0.78
     этой
    0.75
     této
    0.75
    这项
    0.73
     această
    0.72
     melakukannya
    0.72
     它
    0.69
     इसको
    0.68
    Act Density 0.036%

    No Known Activations