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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Scaffold
    -0.07
    -connect
    -0.06
     Chance
    -0.06
    FOUNDATION
    -0.06
     Dob
    -0.06
     cam
    -0.06
     tiên
    -0.06
     roasted
    -0.06
     Cam
    -0.06
    tracks
    -0.06
    POSITIVE LOGITS
    StringRef
    0.07
    YPES
    0.06
     Gerry
    0.06
     pessim
    0.06
    rng
    0.06
    763
    0.06
     Recover
    0.06
     ).↵
    0.06
    부터
    0.06
     Registro
    0.06
    Act Density 0.000%

    No Known Activations