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

    Neuronpedia

    INDEX
    Explanations

    specifies exactly, wins, CRT only

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    periodic
    0.46
    correlated
    0.44
    installment
    0.40
    Outlet
    0.40
    璺
    0.39
    rages
    0.39
     अनुसरण
    0.39
    Resident
    0.38
     automóviles
    0.38
    ксе
    0.38
    POSITIVE LOGITS
    㯎
    0.45
     peeling
    0.42
    iteits
    0.42
     Discussions
    0.40
     Dob
    0.40
     peeled
    0.40
    ತ್
    0.38
     Technol
    0.38
     perfused
    0.38
     Blank
    0.38
    Act Density 0.002%

    No Known Activations