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

    Neuronpedia

    INDEX
    Explanations

    champion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    706
    -0.07
    -license
    -0.06
    iale
    -0.06
    _met
    -0.06
     Malcolm
    -0.06
    iscal
    -0.06
     guten
    -0.06
     Wood
    -0.06
     Grad
    -0.06
    業
    -0.05
    POSITIVE LOGITS
    .communic
    0.07
    extends
    0.07
     xlink
    0.07
     MonoBehaviour
    0.06
     PRIMARY
    0.06
    .qq
    0.06
     commit
    0.06
     yg
    0.06
     FUN
    0.06
    >'.$
    0.06
    Act Density 0.011%

    No Known Activations