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

    Neuronpedia

    INDEX
    Explanations

    differences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Y
    -0.07
    y
    -0.07
    .construct
    -0.07
     состояния
    -0.07
     WEST
    -0.07
    Heap
    -0.06
     headed
    -0.06
    ेशन
    -0.06
    PLAN
    -0.06
     coast
    -0.06
    POSITIVE LOGITS
     differences
    0.09
     differ
    0.09
     differed
    0.09
     Differences
    0.08
    /disc
    0.08
     difference
    0.07
    ่อส
    0.07
    _diff
    0.07
     разви
    0.07
    ictured
    0.07
    Act Density 0.033%

    No Known Activations