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

    Neuronpedia

    INDEX
    Explanations

    string literal unexpected

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Compound
    0.43
     Curious
    0.41
    ম
    0.40
     Compound
    0.40
    名称
    0.40
     Lorem
    0.39
    Core
    0.39
    \
    0.38
    נו
    0.38
    riert
    0.37
    POSITIVE LOGITS
    yes
    0.50
    YES
    0.47
    yeah
    0.44
     yes
    0.42
     ใช่
    0.42
    ใช่
    0.41
    Yes
    0.40
     الاثنين
    0.38
     true
    0.38
    ytics
    0.37
    Act Density 0.008%

    No Known Activations