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

    Neuronpedia

    INDEX
    Explanations

    under, license

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cke
    -0.30
    åĬ²
    -0.29
    lest
    -0.27
    ุà¸Ķ
    -0.24
     regenerated
    -0.24
     MASS
    -0.24
    æľ¬ç½ij
    -0.24
    äºĶ大
    -0.24
    åĭģ
    -0.24
     treat
    -0.24
    POSITIVE LOGITS
    æī¿åıĹ
    0.28
    åħįç¨İ
    0.25
    éĥı
    0.25
     sensitive
    0.24
    Responder
    0.24
    -sensitive
    0.24
     ComVisible
    0.24
    reflect
    0.24
    webpack
    0.24
    rovers
    0.24
    Act Density 0.019%

    No Known Activations