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

    Neuronpedia

    INDEX
    Explanations

    currency or price

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    综
    0.40
     Server
    0.39
    atici
    0.38
     Kon
    0.38
     Plane
    0.38
     Farben
    0.36
    ु
    0.35
     recycler
    0.35
    вед
    0.34
     Fenster
    0.34
    POSITIVE LOGITS
     tampoco
    0.64
     نہیں
    0.45
    Similarly
    0.40
     algunas
    0.39
     algumas
    0.39
    elijke
    0.38
    𝗖
    0.37
    irp
    0.37
    nope
    0.37
    While
    0.36
    Act Density 0.085%

    No Known Activations