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

    Neuronpedia

    INDEX
    Explanations

    Barnaby

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     magnetization
    0.38
    enio
    0.37
     electrolyte
    0.37
     electrolytic
    0.37
     recycling
    0.36
     impe
    0.36
     electrolytes
    0.36
     elektrol
    0.35
     pem
    0.35
     Immobil
    0.34
    POSITIVE LOGITS
    JAM
    0.38
    क्त
    0.37
    Native
    0.37
     abreast
    0.37
    Dense
    0.35
     jammed
    0.35
    native
    0.35
    Trou
    0.34
    BC
    0.34
    ielsen
    0.34
    Act Density 0.029%

    No Known Activations