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

    Neuronpedia

    INDEX
    Explanations

    dark city paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Если
    0.49
    prove
    0.49
     Prove
    0.48
    Prove
    0.48
    或
    0.47
     remov
    0.47
     अथवा
    0.46
     увеличить
    0.46
     величина
    0.46
    6
    0.46
    POSITIVE LOGITS
     Houses
    0.43
    മായ
    0.43
     housed
    0.42
     Habsburg
    0.41
     hails
    0.40
    koord
    0.40
     blieb
    0.40
     Labour
    0.40
     맞아
    0.39
     schn
    0.39
    Act Density 0.005%

    No Known Activations