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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Lin
    -0.07
    Hang
    -0.07
     drifting
    -0.07
     Candy
    -0.06
     negocio
    -0.06
    Adjacent
    -0.06
    ộc
    -0.06
     sabotage
    -0.06
    цем
    -0.06
     diner
    -0.06
    POSITIVE LOGITS
    .Product
    0.07
    .remove
    0.07
    ___
    0.06
    "][
    0.06
    \Contracts
    0.06
    列
    0.06
     byt
    0.06
     productName
    0.06
     appel
    0.06
    RCT
    0.06
    Act Density 0.028%

    No Known Activations