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

    Neuronpedia

    INDEX
    Explanations

    mental healthcare, shapewear, head trauma

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wretched
    0.32
     Länge
    0.31
     capitán
    0.31
     adimensional
    0.31
     asunto
    0.31
     amiable
    0.30
    talet
    0.30
    kannt
    0.30
    }$;
    0.29
     Leibn
    0.29
    POSITIVE LOGITS
     and
    0.44
    /
    0.39
    -
    0.39
     ও
    0.37
    ুর
    0.34
    -/
    0.32
    相关的
    0.32
    -,
    0.31
    ,【
    0.30
    和
    0.29
    Act Density 0.499%

    No Known Activations