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

    Neuronpedia

    INDEX
    Explanations

    schedule messages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ARN
    0.49
     dor
    0.48
     IX
    0.48
     X
    0.47
     friends
    0.47
     đạo
    0.46
     arg
    0.46
     den
    0.46
     amigos
    0.44
     Dor
    0.44
    POSITIVE LOGITS
    xcuserdatad
    0.42
    bereit
    0.42
    eled
    0.40
    껴
    0.39
    ioides
    0.39
    Setpoint
    0.38
    𝖐
    0.37
    ppins
    0.37
    Duties
    0.37
    箐
    0.37
    Act Density 0.000%

    No Known Activations