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

    Neuronpedia

    INDEX
    Explanations

    phone numbers and codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     componentDid
    0.36
    auern
    0.35
     narratives
    0.33
    とその
    0.33
    న్ని
    0.33
    uggest
    0.33
     attracts
    0.32
    では
    0.32
     насла
    0.31
    啮
    0.31
    POSITIVE LOGITS
     B
    0.43
     D
    0.40
     jeweil
    0.38
     P
    0.37
     U
    0.37
     R
    0.36
     N
    0.36
    𝐫
    0.36
     kilómetros
    0.35
     J
    0.35
    Act Density 0.001%

    No Known Activations