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

    Neuronpedia

    INDEX
    Explanations

    ="

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /buttons
    -0.07
     ship
    -0.07
     RPC
    -0.07
     Cut
    -0.07
    URES
    -0.07
    sprites
    -0.06
     swipe
    -0.06
     Soap
    -0.06
    .tab
    -0.06
     PB
    -0.06
    POSITIVE LOGITS
    cos
    0.06
    oulouse
    0.06
     assemble
    0.06
     unlocks
    0.06
     قانون
    0.06
    抗
    0.06
    executable
    0.06
    اوية
    0.06
    dere
    0.06
     мот
    0.06
    Act Density 0.000%

    No Known Activations