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

    Neuronpedia

    INDEX
    Explanations

    conditions, everyday phrasing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    benzoic
    0.56
     መ
    0.53
    galactic
    0.51
     اجتما
    0.49
     গুরুত্বপূর্ণ
    0.47
     ప్ర
    0.46
    Jw
    0.46
    idalgo
    0.46
    akers
    0.45
    ូល
    0.44
    POSITIVE LOGITS
     suffix
    0.51
     ungu
    0.49
     EMF
    0.46
     two
    0.45
     minor
    0.45
     Two
    0.44
     uses
    0.44
     WIT
    0.44
     temperature
    0.44
     fo
    0.43
    Act Density 0.007%

    No Known Activations