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

    Neuronpedia

    INDEX
    Explanations

    friendly

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     December
    -0.07
     cycles
    -0.06
     presum
    -0.06
     coup
    -0.06
     cycle
    -0.06
     Meter
    -0.06
    [cell
    -0.06
     November
    -0.06
    .Acc
    -0.06
     maximize
    -0.06
    POSITIVE LOGITS
     friendly
    0.10
    -friendly
    0.09
    riendly
    0.08
    ,ID
    0.07
     stance
    0.07
    tığ
    0.07
    INST
    0.07
    (fieldName
    0.07
    ственный
    0.07
    RICS
    0.07
    Act Density 0.012%

    No Known Activations