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

    Neuronpedia

    INDEX
    Explanations

    Intestinal procedures

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Understanding
    -0.07
     Nun
    -0.07
    -centric
    -0.07
     vets
    -0.06
    Steel
    -0.06
     decent
    -0.06
    renom
    -0.06
    /*↵
    -0.06
    Update
    -0.06
    pNext
    -0.06
    POSITIVE LOGITS
     solidarity
    0.07
    áct
    0.06
    isible
    0.06
     협
    0.06
     HACK
    0.06
     MODIFY
    0.06
     acted
    0.06
     hintText
    0.06
    �
    0.06
    Strict
    0.06
    Act Density 0.017%

    No Known Activations