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

    Neuronpedia

    INDEX
    Explanations

    journal reference

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     right
    -0.08
    boot
    -0.07
    _help
    -0.07
     свет
    -0.07
     well
    -0.07
     King
    -0.07
     set
    -0.07
     Dong
    -0.07
     wil
    -0.07
    approve
    -0.07
    POSITIVE LOGITS
    195
    0.08
     Elvis
    0.08
     Cassidy
    0.07
    657
    0.07
     fas
    0.07
    MAS
    0.07
    152
    0.07
     Lydia
    0.07
    857
    0.07
    umba
    0.07
    Act Density 0.144%

    No Known Activations