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

    Neuronpedia

    INDEX
    Explanations

    humanities, obligation, acquisition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ע
    0.55
    Tr
    0.55
     exaggerate
    0.55
    Під
    0.53
    V
    0.50
     exagger
    0.49
    по
    0.49
     usur
    0.47
    ка
    0.47
     with
    0.47
    POSITIVE LOGITS
     jurusan
    0.48
     idha
    0.46
     ditth
    0.46
    人文
    0.46
    shims
    0.46
     erc
    0.45
    િલ
    0.44
    echolog
    0.44
     হইলেন
    0.43
    nucleon
    0.43
    Act Density 0.001%

    No Known Activations