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

    Neuronpedia

    INDEX
    Explanations

    list

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     öne
    -0.08
     karşısında
    -0.07
     Flow
    -0.07
    -section
    -0.07
    rian
    -0.06
     advancing
    -0.06
    IVING
    -0.06
    _RECT
    -0.06
     RUN
    -0.06
     ROM
    -0.06
    POSITIVE LOGITS
    紀
    0.07
    ๕
    0.06
    ₁
    0.06
    haf
    0.06
     sq
    0.06
     Pepsi
    0.06
    lit
    0.06
     fputs
    0.06
     Sous
    0.06
    _firstname
    0.06
    Act Density 0.025%

    No Known Activations