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

    Neuronpedia

    INDEX
    Explanations

    referencing sections or notes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kecepatan
    0.28
    "=>$
    0.26
    ਝ
    0.26
     ($\
    0.26
    াদিগকে
    0.26
    ామని
    0.26
    unghi
    0.25
    <unused59>
    0.25
     necesitamos
    0.25
     prototyp
    0.25
    POSITIVE LOGITS
     Wikipedia
    0.59
    Wikipedia
    0.56
     official
    0.54
     section
    0.51
     https
    0.50
     wikipedia
    0.50
     LinkedIn
    0.49
    https
    0.48
    wikipedia
    0.46
     Google
    0.46
    Act Density 0.139%

    No Known Activations