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

    Neuronpedia

    INDEX
    Explanations

    Building success

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     préoccup
    -0.08
     zon
    -0.08
     stolz
    -0.08
    GRAM
    -0.08
     дым
    -0.08
     дух
    -0.08
    цам
    -0.08
     جد
    -0.08
     고민
    -0.08
     دغ
    -0.07
    POSITIVE LOGITS
     binding
    0.10
     indivíduo
    0.09
    binding
    0.09
     interpersonal
    0.09
     Binding
    0.09
     cognitive
    0.08
     trait
    0.08
    ierte
    0.08
    .binding
    0.08
     Cognitive
    0.08
    Act Density 0.060%

    No Known Activations