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

    Neuronpedia

    INDEX
    Explanations

    note taking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.50
     extravagance
    0.47
     ಒತ್ತ
    0.47
     ram
    0.47
     pomp
    0.45
     Chongqing
    0.45
     extravagant
    0.44
     CERN
    0.44
     MFA
    0.44
     hagg
    0.43
    POSITIVE LOGITS
    🥗
    0.48
    Ду
    0.47
    배
    0.46
    Algun
    0.46
     debemos
    0.46
    endous
    0.46
     presentamos
    0.45
    旪
    0.45
    Ле
    0.45
     grupa
    0.44
    Act Density 0.002%

    No Known Activations