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

    Neuronpedia

    INDEX
    Explanations

    Code quotations/asterisks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    よ
    -0.08
    셉
    -0.07
    简便
    -0.07
    _iff
    -0.07
    葴
    -0.06
     wyposaż
    -0.06
    ⿻
    -0.06
     Kb
    -0.06
    .tie
    -0.06
    に基
    -0.06
    POSITIVE LOGITS
    ematics
    0.08
     ")
↵
    0.08
     producer
    0.07
    <Entry
    0.07
    Agent
    0.07
     monet
    0.07
    IMAGE
    0.07
    OPLE
    0.07
    ASSES
    0.07
     |
↵
    0.07
    Act Density 0.004%

    No Known Activations