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

    Neuronpedia

    INDEX
    Explanations

    rated

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nast
    -0.07
    safe
    -0.06
     buses
    -0.06
    pro
    -0.06
     penalty
    -0.06
    382
    -0.06
    .social
    -0.06
     cyn
    -0.06
     nob
    -0.06
    .tax
    -0.06
    POSITIVE LOGITS
     profoundly
    0.06
     GetComponent
    0.06
     Researchers
    0.06
    .Logf
    0.06
    -dominated
    0.06
    .startswith
    0.06
     traveler
    0.06
     FE
    0.06
    angler
    0.06
    CEED
    0.06
    Act Density 0.008%

    No Known Activations