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

    Neuronpedia

    INDEX
    Explanations

    I will respond

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     enemies
    0.45
    但是
    0.40
     despite
    0.40
     olsa
    0.39
     any
    0.38
    但是在
    0.38
     maybe
    0.36
     immunology
    0.36
     ακόμη
    0.36
     values
    0.36
    POSITIVE LOGITS
    それを
    0.61
     entsprechende
    0.59
     तुरंत
    0.54
     correspondingly
    0.54
    予以
    0.51
     그걸
    0.51
     entsprechenden
    0.50
     उन्हें
    0.50
     त्यांना
    0.49
     તેને
    0.48
    Act Density 0.255%

    No Known Activations