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

    Neuronpedia

    INDEX
    Explanations

    geometry and tangent circles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     budgeting
    -0.10
     감사합니다
    -0.08
     donations
    -0.07
     Budget
    -0.07
     сус
    -0.07
     submitted
    -0.07
    DBC
    -0.07
     summons
    -0.07
    uffed
    -0.07
     pension
    -0.07
    POSITIVE LOGITS
    雙
    0.08
     gemeinsamen
    0.08
     दोनों
    0.08
     cuer
    0.08
    双
    0.08
    �
    0.08
    思思
    0.08
     cuad
    0.08
    ्लेष
    0.08
    Deux
    0.08
    Act Density 0.033%

    No Known Activations