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

    Neuronpedia

    INDEX
    Explanations

    BSD

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     assist
    -0.08
    _maker
    -0.07
    _loading
    -0.07
    texts
    -0.07
     حمل
    -0.06
     inequality
    -0.06
     Initialization
    -0.06
     gadget
    -0.06
     Police
    -0.06
     classifier
    -0.06
    POSITIVE LOGITS
    TEE
    0.06
    AAAA
    0.06
    指数
    0.06
    _months
    0.06
    XB
    0.06
     cass
    0.06
     '__
    0.06
    KB
    0.06
    OR
    0.06
     Chromium
    0.06
    Act Density 0.001%

    No Known Activations