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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     CLR
    -0.06
     mú
    -0.06
    ायत
    -0.06
    şa
    -0.06
     दब
    -0.06
     شیر
    -0.06
    \Entity
    -0.06
     pirates
    -0.06
     linger
    -0.06
    weeney
    -0.06
    POSITIVE LOGITS
    อป
    0.08
    ################
    0.07
    .heap
    0.07
     температуры
    0.07
     آمریک
    0.07
    	delete
    0.06
    readonly
    0.06
    ору
    0.06
    %x
    0.06
    verse
    0.06
    Act Density 0.002%

    No Known Activations