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

    Neuronpedia

    INDEX
    Explanations

    structured conceptual technologies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    簟
    0.25
    Wearing
    0.25
    精华
    0.25
    劇
    0.25
    યા
    0.25
     நாடுக
    0.24
     idk
    0.24
    }$;
    0.24
     foncé
    0.24
     aren
    0.24
    POSITIVE LOGITS
    -
    0.36
    _
    0.35
    -,
    0.29
     architectures
    0.29
    funding
    0.29
     technologies
    0.28
    izing
    0.27
     or
    0.27
     policing
    0.26
     funding
    0.26
    Act Density 0.337%

    No Known Activations