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

    Neuronpedia

    INDEX
    Explanations

    better

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Gaut
    -0.33
    usk
    -0.28
    igor
    -0.27
    çĽ´è¾¾
    -0.27
    没æľīä»»ä½ķ
    -0.26
     viewed
    -0.26
    è§Ĩ
    -0.25
    ë§ī
    -0.25
    bounce
    -0.24
    uelle
    -0.24
    POSITIVE LOGITS
    ä¸įæĸ¹ä¾¿
    0.27
    ders
    0.27
     equivalents
    0.25
    ycl
    0.24
     concent
    0.24
     correlated
    0.24
     translating
    0.24
     disciplines
    0.24
    åĬłéĢŁ
    0.24
    deaux
    0.23
    Act Density 0.040%

    No Known Activations