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

    Neuronpedia

    INDEX
    Explanations

    which

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     head
    -0.07
     civilized
    -0.07
    acterial
    -0.06
    ditor
    -0.06
     agr
    -0.06
    metadata
    -0.06
    اسه
    -0.06
    oving
    -0.06
    Roman
    -0.06
    theory
    -0.06
    POSITIVE LOGITS
    ็ตาม
    0.06
    aims
    0.06
     }}/
    0.06
     aplikace
    0.06
    OutOfRange
    0.06
    均
    0.06
    並
    0.06
    asyarakat
    0.06
     discard
    0.06
    /system
    0.06
    Act Density 0.298%

    No Known Activations