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

    Neuronpedia

    INDEX
    Explanations

    business change

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SOAP
    -0.06
    ,unsigned
    -0.06
     zal
    -0.06
     :.
    -0.06
    omitempty
    -0.06
    .ot
    -0.06
    内部
    -0.06
     Nicholson
    -0.06
     domingo
    -0.06
     escalating
    -0.06
    POSITIVE LOGITS
     rout
    0.07
    .FlatStyle
    0.07
    Density
    0.06
     gravy
    0.06
     PYTHON
    0.06
    ycz
    0.06
    .todo
    0.06
     DSL
    0.06
    stroy
    0.06
     bra
    0.06
    Act Density 0.166%

    No Known Activations