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

    Neuronpedia

    INDEX
    Explanations

    create

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     halt
    -0.07
     lob
    -0.07
    lbs
    -0.07
     obstacle
    -0.07
    Localization
    -0.07
     lb
    -0.07
     Suff
    -0.06
    LOUD
    -0.06
     flush
    -0.06
     oh
    -0.06
    POSITIVE LOGITS
    CreateDate
    0.07
    현
    0.07
    àm
    0.07
     curing
    0.07
    (cin
    0.07
    われ
    0.07
    _RST
    0.06
     cultivation
    0.06
    made
    0.06
    /Product
    0.06
    Act Density 0.029%

    No Known Activations