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

    Neuronpedia

    INDEX
    Explanations

    Code with loops and indexing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    èm
    -0.07
    pet
    -0.06
     merit
    -0.06
    WebpackPlugin
    -0.06
     crashes
    -0.06
    ата
    -0.06
    hibited
    -0.06
    аться
    -0.06
    LAR
    -0.06
    Span
    -0.06
    POSITIVE LOGITS
    \C
    0.07
     escalate
    0.06
     �
    0.06
     isot
    0.06
    Contract
    0.06
     "";↵↵
    0.06
     한번
    0.06
    .df
    0.06
     Confirm
    0.06
     بعضی
    0.06
    Act Density 0.025%

    No Known Activations