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

    Neuronpedia

    INDEX
    Explanations

    then

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ikinci
    -0.07
     advocacy
    -0.06
     Δια
    -0.06
     vzdu
    -0.06
     gens
    -0.06
    POL
    -0.06
     Flood
    -0.06
    epad
    -0.06
     loi
    -0.06
    blocks
    -0.06
    POSITIVE LOGITS
    еб
    0.07
    �
    0.07
    .then
    0.07
     beneficial
    0.07
    出来
    0.06
    \Json
    0.06
    illusion
    0.06
    ToString
    0.06
    Either
    0.06
    戲
    0.06
    Act Density 0.001%

    No Known Activations