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

    Neuronpedia

    INDEX
    Explanations

    bringing manufacturing back

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gepub
    0.59
    š
    0.58
     to
    0.57
    yczy
    0.55
    ியுள்ளது
    0.55
     jeste
    0.55
    ITHUB
    0.55
     재미
    0.55
    的海
    0.54
     </
    0.53
    POSITIVE LOGITS
    ag
    0.58
     conditioners
    0.58
    ↵
    0.56
    F
    0.55
     contingencies
    0.55
    mming
    0.54
     transducers
    0.54
     tracers
    0.54
    R
    0.54
     एंड
    0.53
    Act Density 0.000%

    No Known Activations