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

    Neuronpedia

    INDEX
    Explanations

    establishing burden

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     degrees
    -0.07
    카
    -0.06
     jours
    -0.06
     stakes
    -0.06
    (a
    -0.06
    .qu
    -0.06
    Markers
    -0.06
    Gender
    -0.06
     flatt
    -0.06
     Resolution
    -0.06
    POSITIVE LOGITS
     polov
    0.07
     incontr
    0.06
     Ос
    0.06
    -Cds
    0.06
    ACP
    0.06
    Accessory
    0.06
    pcb
    0.06
    restriction
    0.06
    oot
    0.06
    UsageId
    0.06
    Act Density 0.005%

    No Known Activations