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

    Neuronpedia

    INDEX
    Explanations

    telemetry

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    പ്പറ
    1.28
     Lamps
    1.25
    ន់
    1.18
     Provision
    1.16
    ParamNum
    1.15
    ículos
    1.11
     कार्यकर्त्या
    1.11
     فونٹ
    1.10
    LENGTH
    1.10
    RationalValue
    1.08
    POSITIVE LOGITS
    iet
    1.08
    িশালী
    1.07
    ই
    1.00
    可以看到
    1.00
    o
    0.98
    รา
    0.95
    め
    0.89
    mazing
    0.89
    Pale
    0.88
    owanie
    0.86
    Act Density 0.001%

    No Known Activations