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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Depth
    -0.06
     chips
    -0.06
     stě
    -0.06
    balls
    -0.06
     fak
    -0.06
     자기
    -0.06
     stationary
    -0.06
    field
    -0.06
     busy
    -0.06
     chip
    -0.06
    POSITIVE LOGITS
    pellier
    0.07
     rhythms
    0.06
    hatt
    0.06
     香港
    0.06
     inev
    0.06
     ноября
    0.06
    ective
    0.06
     nắng
    0.06
     became
    0.06
     травня
    0.06
    Act Density 0.016%

    No Known Activations