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

    Neuronpedia

    INDEX
    Explanations

    increasing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ses
    -0.07
     Cylinder
    -0.07
    ि,
    -0.06
     yu
    -0.06
     sunny
    -0.06
    gnu
    -0.06
     şarkı
    -0.06
    _intr
    -0.06
    */,
    -0.06
     Track
    -0.06
    POSITIVE LOGITS
     lesbisk
    0.06
     swaps
    0.06
    ']>
    0.06
    odox
    0.06
     skb
    0.06
     genuinely
    0.06
    麦
    0.06
     boxed
    0.06
     salts
    0.06
     потрібно
    0.06
    Act Density 0.045%

    No Known Activations