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

    Neuronpedia

    INDEX
    Explanations

    hole

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Rad
    -0.07
    riend
    -0.07
     baker
    -0.07
    )>
    -0.07
    子供
    -0.06
     wider
    -0.06
     engr
    -0.06
     caregiver
    -0.06
    Uni
    -0.06
    .Parcelable
    -0.06
    POSITIVE LOGITS
     Hole
    0.11
    洞
    0.09
    OLE
    0.09
     hole
    0.08
    ole
    0.08
     Whole
    0.07
     Shot
    0.07
    hole
    0.07
     Fault
    0.07
     pole
    0.07
    Act Density 0.012%

    No Known Activations