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

    Neuronpedia

    INDEX
    Explanations

    rewrite

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oc
    -0.08
     }
    -0.07
    .exceptions
    -0.07
     }}
    -0.06
    MOTE
    -0.06
    (".
    -0.06
    +z
    -0.06
     "></
    -0.06
    .subject
    -0.06
     yola
    -0.06
    POSITIVE LOGITS
     rewriting
    0.17
     rewritten
    0.15
     rewrite
    0.12
     rew
    0.08
     Rewrite
    0.08
     Rew
    0.07
    write
    0.07
    WRITE
    0.07
    ritten
    0.07
     déf
    0.06
    Act Density 0.005%

    No Known Activations