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

    Neuronpedia

    INDEX
    Explanations

    Toronto

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .error
    -0.07
    (value
    -0.07
     unlaw
    -0.07
     Politics
    -0.07
    ffic
    -0.07
    lpVtbl
    -0.07
     vomiting
    -0.06
     flew
    -0.06
     Addiction
    -0.06
    ㎄
    -0.06
    POSITIVE LOGITS
    ^\
    0.07
    stay
    0.07
    needle
    0.07
    爐
    0.07
    ])),
    0.07
    ----</
    0.07
     Resorts
    0.07
     cheered
    0.07
     ngại
    0.07
    sortBy
    0.06
    Act Density 0.093%

    No Known Activations