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

    Neuronpedia

    INDEX
    Explanations

    D

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ersive
    -0.26
     Fres
    -0.25
    -slot
    -0.24
     impover
    -0.24
    åľ¨ç½ij绾
    -0.24
     Frames
    -0.24
    bread
    -0.24
    armor
    -0.24
     privileges
    -0.24
    ays
    -0.23
    POSITIVE LOGITS
    #{
    0.31
    egral
    0.26
    èĻŁ
    0.25
     urban
    0.25
    urban
    0.25
     cott
    0.25
    OTOS
    0.24
    celona
    0.24
    anian
    0.24
    oÅĽÄĩ
    0.24
    Act Density 0.002%

    No Known Activations