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

    Neuronpedia

    INDEX
    Explanations

    storage

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pisc
    -0.07
    /ml
    -0.06
     соци
    -0.06
     unity
    -0.06
    (th
    -0.06
    (tweet
    -0.06
     conc
    -0.06
     też
    -0.06
     autobiography
    -0.06
    يلم
    -0.06
    POSITIVE LOGITS
    品
    0.07
     crackers
    0.06
     unrestricted
    0.06
     어머니
    0.06
    �
    0.06
    ださい
    0.06
     sprink
    0.06
    Amy
    0.06
    Sock
    0.06
    eper
    0.06
    Act Density 0.024%

    No Known Activations