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

    Neuronpedia

    INDEX
    Explanations

    markdown headings and GET requests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     prer
    0.47
     república
    0.46
     excitations
    0.46
     vehicular
    0.45
     convexo
    0.45
     paramilitary
    0.44
     complica
    0.44
     equilibria
    0.43
     territorios
    0.43
     ASSERT
    0.43
    POSITIVE LOGITS
    ポイント
    0.43
     changement
    0.40
     Determines
    0.39
     Punkt
    0.39
     Identifying
    0.39
     Times
    0.38
    ப்பர்
    0.38
    ोन
    0.38
    शोर
    0.38
    endaftaran
    0.38
    Act Density 0.002%

    No Known Activations