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

    Neuronpedia

    INDEX
    Explanations

    on and offboarding / ramp / demand

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     สาว
    0.44
     eqn
    0.42
     injustices
    0.41
     scrollTop
    0.41
     drewn
    0.40
    াদেশ
    0.40
     pls
    0.39
    ান্ত
    0.39
     लेख
    0.39
    意见
    0.39
    POSITIVE LOGITS
     off
    0.66
    Off
    0.64
     On
    0.60
     Off
    0.59
    on
    0.59
    í
    0.59
    On
    0.57
     on
    0.57
     OFF
    0.55
    オン
    0.55
    Act Density 0.016%

    No Known Activations