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

    Neuronpedia

    INDEX
    Explanations

    Inscriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bend
    -0.07
     الثالث
    -0.07
     McGr
    -0.06
    _organization
    -0.06
     dgv
    -0.06
     Officials
    -0.06
    _True
    -0.06
     european
    -0.06
    Cube
    -0.06
     Hamp
    -0.06
    POSITIVE LOGITS
    oug
    0.07
     survived
    0.06
     sailing
    0.06
     Clarence
    0.06
    =name
    0.06
    INUE
    0.06
     einige
    0.06
     листопада
    0.06
    asına
    0.06
     espera
    0.06
    Act Density 0.010%

    No Known Activations