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

    Neuronpedia

    INDEX
    Explanations

    describing items or instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ref
    0.46
     contact
    0.44
     CONTACT
    0.43
     All
    0.42
     Ref
    0.41
    0.41
     Contact
    0.39
     overhead
    0.37
     "
    0.37
     Bergh
    0.37
    POSITIVE LOGITS
    教师
    0.47
     सलाहकार
    0.47
     ಉತ್ತ
    0.47
    Emulator
    0.47
     pelajaran
    0.47
     एक्सप्लेन
    0.46
    0.46
    και
    0.45
    🗸
    0.45
    पीरियंस
    0.45
    Act Density 0.000%

    No Known Activations