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

    Neuronpedia

    INDEX
    Explanations

    want

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sunday
    -0.06
    �
    -0.06
     torch
    -0.06
    设备
    -0.06
     carrier
    -0.06
    цев
    -0.06
    forces
    -0.06
     경북
    -0.06
    特殊
    -0.06
    (go
    -0.06
    POSITIVE LOGITS
     Choi
    0.07
     Lans
    0.06
     analsex
    0.06
    -valu
    0.06
    cosa
    0.06
     infuri
    0.06
     착
    0.06
     تص
    0.06
     الشم
    0.06
     Land
    0.06
    Act Density 0.001%

    No Known Activations