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

    Neuronpedia

    INDEX
    Explanations

    Higher power/religion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     р
    -0.06
    杨
    -0.06
    hoo
    -0.06
     суб
    -0.06
     důsled
    -0.06
    sn
    -0.06
    #index
    -0.06
     fictional
    -0.06
     мира
    -0.06
    irket
    -0.05
    POSITIVE LOGITS
     Pose
    0.07
     пла
    0.07
    .Grid
    0.06
    Bold
    0.06
    .Unlock
    0.06
    seudo
    0.06
     defa
    0.06
    /git
    0.06
     flank
    0.06
     potato
    0.06
    Act Density 0.025%

    No Known Activations