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

    Neuronpedia

    INDEX
    Explanations

    ke

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    comboBox
    0.40
     electrons
    0.38
     preliminary
    0.36
     अवेलेबल
    0.36
     ured
    0.36
     Technol
    0.35
    avourable
    0.35
    ู
    0.35
     સી
    0.34
    rew
    0.34
    POSITIVE LOGITS
    LINES
    0.39
    Passenger
    0.39
     দেখানো
    0.38
    𒉌
    0.38
    Famil
    0.38
     lines
    0.37
    GRE
    0.37
    Dallas
    0.37
     passenger
    0.36
     чаще
    0.36
    Act Density 0.008%

    No Known Activations