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

    Neuronpedia

    INDEX
    Explanations

    colors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /print
    -0.07
     Simone
    -0.06
    imageUrl
    -0.06
    vit
    -0.06
    uire
    -0.06
    ISH
    -0.06
     balk
    -0.06
    pcs
    -0.06
    вели
    -0.06
    了过来
    -0.06
    POSITIVE LOGITS
     reasonably
    0.07
    .How
    0.07
    cities
    0.07
     Hammond
    0.07
      
    0.07
     focused
    0.07
    รส
    0.07
    .requests
    0.07
    .Resume
    0.06
     creatures
    0.06
    Act Density 0.014%

    No Known Activations