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

    Neuronpedia

    INDEX
    Explanations

    have

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Optionally
    -0.07
    KeyId
    -0.07
    .Rectangle
    -0.06
    xDD
    -0.06
    атку
    -0.06
    領
    -0.06
    +)\
    -0.06
    Idx
    -0.06
    _cmds
    -0.06
     Tu
    -0.06
    POSITIVE LOGITS
    із
    0.07
     بات
    0.06
     supern
    0.06
    spots
    0.06
    (cos
    0.06
    Vehicle
    0.06
    remium
    0.06
    record
    0.06
     appreh
    0.06
    >());↵↵
    0.06
    Act Density 0.001%

    No Known Activations