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

    Neuronpedia

    INDEX
    Explanations

    creation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     utmost
    -0.07
     obedience
    -0.07
     upright
    -0.07
     лучше
    -0.07
    Bone
    -0.07
     Moore
    -0.07
     wal
    -0.06
     september
    -0.06
     salle
    -0.06
    Intro
    -0.06
    POSITIVE LOGITS
     creator
    0.08
     creation
    0.08
    ayload
    0.07
     createdAt
    0.07
    VarInsn
    0.07
    er
    0.07
     Abram
    0.06
    ardown
    0.06
    ers
    0.06
     caster
    0.06
    Act Density 0.031%

    No Known Activations