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

    Neuronpedia

    INDEX
    Explanations

    abstract concepts or complicated situations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     a
    0.44
     the
    0.43
     an
    0.38
    }
    0.33
    0
    0.32
     {
    0.31
     à
    0.31
    hout
    0.30
    the
    0.30
    {
    0.30
    POSITIVE LOGITS
    য়েছে
    0.38
     demise
    0.34
     plight
    0.33
    য়েছে
    0.32
     resurgence
    0.32
     navn
    0.32
     predicament
    0.32
     incarnation
    0.30
    ക്കായി
    0.30
     prerogative
    0.30
    Act Density 0.068%

    No Known Activations