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
     Cel
    -0.08
     CID
    -0.07
     stripes
    -0.07
     dépos
    -0.07
    沒
    -0.07
    Stripe
    -0.07
    �
    -0.07
     Strat
    -0.07
     Straßen
    -0.07
     stripe
    -0.07
    POSITIVE LOGITS
     позитив
    0.12
     सकारात्मक
    0.11
     positivity
    0.11
     vivir
    0.10
     negativity
    0.10
     positivas
    0.10
     pensamientos
    0.09
    shift
    0.09
     gratitude
    0.09
     hábitos
    0.09
    Act Density 0.029%

    No Known Activations