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

    Neuronpedia

    INDEX
    Explanations

    say

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     jane
    -0.07
    ateur
    -0.06
    raison
    -0.06
    imple
    -0.06
    _positive
    -0.06
     �
    -0.06
    opo
    -0.06
     www
    -0.06
     VStack
    -0.06
    談
    -0.06
    POSITIVE LOGITS
    cpy
    0.07
    /tasks
    0.06
     Bash
    0.06
    873
    0.06
    Christ
    0.06
     Pine
    0.06
     chce
    0.06
    Aug
    0.06
     ruined
    0.06
     برگزار
    0.06
    Act Density 0.020%

    No Known Activations