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

    Neuronpedia

    INDEX
    Explanations

    Placing Germany

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     banget
    0.46
     aggrieved
    0.46
     dấu
    0.42
     mammary
    0.41
     erstwhile
    0.41
     exemplar
    0.41
     them
    0.40
    を変
    0.40
     bairro
    0.40
     Zamora
    0.40
    POSITIVE LOGITS
     Placing
    0.43
     persönlichen
    0.41
     TITLE
    0.40
     Glasses
    0.40
     Safety
    0.40
     Placement
    0.40
    koord
    0.40
     STEP
    0.39
    führung
    0.39
     Titel
    0.39
    Act Density 0.008%

    No Known Activations