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

    Neuronpedia

    INDEX
    Explanations

    still supported

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     movimentos
    0.39
     wording
    0.38
     movements
    0.38
     behaviors
    0.38
     constraints
    0.38
     टाइप्स
    0.38
     undefined
    0.38
     behaviours
    0.38
    ouvement
    0.38
     semantics
    0.37
    POSITIVE LOGITS
    beza
    0.42
    ನ್ನ
    0.37
     архив
    0.37
     xay
    0.37
    heden
    0.35
    Bz
    0.35
     gz
    0.35
    uximab
    0.35
    琥
    0.35
    ِن
    0.34
    Act Density 0.004%

    No Known Activations