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

    Neuronpedia

    INDEX
    Explanations

    zero

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     давно
    -0.07
     Often
    -0.07
    나
    -0.07
     Afterwards
    -0.07
    、この
    -0.07
    えば
    -0.06
    Later
    -0.06
    \Bridge
    -0.06
     大
    -0.06
    جاج
    -0.06
    POSITIVE LOGITS
     zero
    0.10
     Zero
    0.10
     ZERO
    0.09
    ZERO
    0.07
     tighter
    0.07
    Zero
    0.07
    .getUsername
    0.07
     partners
    0.06
    Partner
    0.06
    0
    0.06
    Act Density 0.007%

    No Known Activations