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

    Neuronpedia

    INDEX
    Explanations

    humanity, criticizing, feelings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     відчу
    0.41
    উপর
    0.39
    现场
    0.38
    组
    0.38
     upay
    0.38
    岀
    0.37
     구성
    0.37
    BuildAction
    0.37
    എന്ന
    0.36
    觉
    0.36
    POSITIVE LOGITS
     sass
    0.46
     sod
    0.39
     taxi
    0.39
     সমালোচনা
    0.39
     sobbing
    0.38
    bursement
    0.38
     szem
    0.36
     worry
    0.36
     pecahan
    0.36
     नीला
    0.35
    Act Density 0.001%

    No Known Activations