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

    Neuronpedia

    INDEX
    Explanations

    probability and letter sequences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Complete
    -0.07
    	dis
    -0.07
     JA
    -0.07
    ,height
    -0.06
    Complete
    -0.06
    _tC
    -0.06
     FEMA
    -0.06
     Most
    -0.06
     Aud
    -0.06
     teach
    -0.06
    POSITIVE LOGITS
    cks
    0.07
     ss
    0.07
    undos
    0.07
    kk
    0.07
    argar
    0.07
     commanders
    0.06
     pp
    0.06
    ircles
    0.06
    Seeder
    0.06
    "So
    0.06
    Act Density 0.029%

    No Known Activations