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

    Neuronpedia

    INDEX
    Explanations

    specifications and references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pensamientos
    0.38
     Gedanken
    0.37
    物語
    0.36
     प्रार
    0.36
     pensamiento
    0.35
    грева
    0.35
    穿
    0.35
    CCCc
    0.34
     здоро
    0.34
    racción
    0.34
    POSITIVE LOGITS
     specifies
    0.38
     specifying
    0.38
     References
    0.38
     specifications
    0.36
     seriously
    0.36
     significance
    0.35
     Significance
    0.35
    he
    0.34
     references
    0.34
    ৃত্বে
    0.34
    Act Density 0.023%

    No Known Activations