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

    Neuronpedia

    INDEX
    Explanations

    External

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dialect
    -0.07
    _SUP
    -0.07
     sedm
    -0.07
     Tôi
    -0.06
     Param
    -0.06
     approval
    -0.06
     topology
    -0.06
     dn
    -0.06
    ixedReality
    -0.06
    회
    -0.06
    POSITIVE LOGITS
    answered
    0.07
    ivamente
    0.07
    acted
    0.07
    ,Y
    0.06
     ofrec
    0.06
    При
    0.06
     vary
    0.06
    Pel
    0.06
    ."""
    0.06
    igung
    0.06
    Act Density 0.003%

    No Known Activations